INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Ge" and its various forms

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

Interstitial

-0.92

ioned

-0.82

æł

-0.75

netflix

-0.73

INGTON

-0.73

ABE

-0.72

kefeller

-0.70

sburgh

-0.69

nesses

-0.69

ividual

-0.69

POSITIVE LOGITS

ffen

1.06

cko

1.04

ORGE

1.00

elong

0.96

orgetown

0.96

ographical

0.95

orget

0.95

og

0.86

gebra

0.84

ometry

0.84

Activations Density 0.011%

proper nouns

occurrences of the word "Ge" and its various forms

No Comments

No Known Activations