INDEX

Explanations

pronouns followed by verbs indicating personal thoughts or opinions

oai_token-act-pair · gpt-3.5-turbo

references to the word "it," indicating a focus on vague or ambiguous subjects

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

 Friend

-0.63

stellar

-0.63

hips

-0.62

 Dayton

-0.60

atlantic

-0.60

ighton

-0.59

idon

-0.59

 Ghana

-0.59

friends

-0.59

 Passenger

-0.58

POSITIVE LOGITS

chy

0.99

unes

0.99

self

0.97

iner

0.92

ueller

0.92

alian

0.87

zik

0.86

ocument

0.79

matter

0.75

fits

0.74

Activations Density 0.165%

pronouns followed by verbs indicating personal thoughts or opinions

references to the word "it," indicating a focus on vague or ambiguous subjects

No Comments

No Known Activations