INDEX

Explanations

phrases related to making choices or decisions

oai_token-act-pair · gpt-3.5-turbo

pronouns and references to individuals or groups

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

vier

-0.73

standing

-0.72

wik

-0.71

gallery

-0.66

Sov

-0.66

ãĥ©ãĥ³

-0.65

lining

-0.64

vine

-0.64

atory

-0.64

iny

-0.63

POSITIVE LOGITS

'd

0.91

'll

0.84

 encountered

0.83

 desired

0.81

 wished

0.78

 wish

0.77

 frequ

0.76

 deems

0.75

 deem

0.75

 ever

0.75

Activations Density 0.122%

phrases related to making choices or decisions

pronouns and references to individuals or groups

No Comments

No Known Activations