INDEX

Explanations

the word "no"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "no" or its variations in different contexts

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

iership

-0.81

realDonaldTrump

-0.72

minster

-0.72

rious

-0.68

lycer

-0.68

RAFT

-0.66

rosse

-0.64

ual

-0.64

idable

-0.63

IUM

-0.62

POSITIVE LOGITS

xious

1.16

zzle

1.00

emi

0.92

 longer

0.91

 matter

0.89

obs

0.88

ise

0.88

terday

0.88

vel

0.87

except

0.81

Activations Density 0.064%

the word "no"

occurrences of the word "no" or its variations in different contexts

No Comments

No Known Activations