INDEX

Explanations

action verbs related to making changes or decisions

oai_token-act-pair · gpt-3.5-turbo

commands or suggestions for actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 guiActiveUnfocused

-0.82

Downloadha

-0.76

 respectively

-0.63

ashington

-0.56

after

-0.55

luster

-0.53

Host

-0.52

>>\

-0.52

quartered

-0.51

BuyableInstoreAndOnline

-0.50

POSITIVE LOGITS

ulate

0.91

 ourselves

0.86

 oneself

0.84

 yourself

0.80

 yourselves

0.76

uate

0.76

iate

0.71

 somet

0.70

 myself

0.70

ayne

0.69

Activations Density 0.645%

action verbs related to making changes or decisions

commands or suggestions for actions

No Comments

No Known Activations