INDEX

Explanations

locations or places commonly associated with names of people or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people and places

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

VALUE

-0.74

SpaceEngineers

-0.70

ATHER

-0.70

ãĤ¯

-0.66

ãĥ¤

-0.66

STR

-0.65

berman

-0.64

å¼

-0.64

Quant

-0.64

Ö¼

-0.64

POSITIVE LOGITS

 Parish

0.82

âĦ¢:

0.82

 Islands

0.75

ilda

0.70

sburg

0.68

helm

0.66

erers

0.65

auga

0.64

Ê

0.62

bian

0.62

Activations Density 0.042%

locations or places commonly associated with names of people or entities

proper nouns, specifically names of people and places

No Comments

No Known Activations