INDEX

Explanations

proper nouns and numbers

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

âĸĵ

-0.57

 comprom

-0.56

advertisement

-0.56

 blockers

-0.55

 inev

-0.54

Sov

-0.52

 aggrav

-0.52

 worrying

-0.51

 icing

-0.51

 outp

-0.50

POSITIVE LOGITS

 âĵĺ

0.83

Joined

0.72

 Died

0.66

itars

0.57

 Posts

0.57

ahu

0.56

 Female

0.52

 Killed

0.52

ometown

0.51

 Sets

0.51

Activations Density 0.796%

proper nouns and numbers

numerical data and statistics

No Comments

No Known Activations