INDEX

Explanations

proper nouns and names

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically brackets and commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 seams

-0.77

 antioxid

-0.69

 potatoes

-0.63

arettes

-0.62

etic

-0.60

 exchanges

-0.59

ãĥ¼ãĥ³

-0.59

cule

-0.58

umble

-0.58

 recipes

-0.57

POSITIVE LOGITS

...]

1.42

Pg

1.28

âĢ¦]

1.26

Footnote

1.10

note

1.07

?]

1.00

:]

0.97

sic

0.93

!]

0.89

](

0.86

Activations Density 0.015%

proper nouns and names

punctuation marks, specifically brackets and commas

No Comments

No Known Activations