INDEX

Explanations

names of organizations or entities, such as "Fiat Chrysler Automobiles" and "Maryhill Winery Tasting Room"

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of companies, places, and significant entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 piping

-0.72

anwhile

-0.71

gently

-0.66

 faint

-0.66

 sheer

-0.65

imately

-0.64

gered

-0.63

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.60

arily

-0.59

successfully

-0.59

POSITIVE LOGITS

Che

0.74

Ps

0.70

Pen

0.67

 Highway

0.66

 Street

0.66

World

0.66

Hack

0.65

Mos

0.64

Sal

0.64

Dun

0.64

Activations Density 0.389%

names of organizations or entities, such as "Fiat Chrysler Automobiles" and "Maryhill Winery Tasting Room"

proper nouns, particularly names of companies, places, and significant entities

No Comments

No Known Activations