INDEX

Explanations

phrases indicating negation or denial

oai_token-act-pair · gpt-3.5-turbo

affirmative statements or declarations

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

iership

-0.91

ãĤ¼ãĤ¦ãĤ¹

-0.71

ript

-0.68

rn

-0.67

RAFT

-0.63

rex

-0.63

tro

-0.63

arthy

-0.62

assies

-0.61

tnc

-0.61

POSITIVE LOGITS

 kidding

1.09

etheless

1.06

 matter

0.94

xious

0.93

 wonder

0.92

zzle

0.92

terday

0.91

 doubt

0.89

 longer

0.89

 Matter

0.82

Activations Density 0.052%

phrases indicating negation or denial

affirmative statements or declarations

No Comments

No Known Activations