INDEX

Explanations

phrases related to awards or titles

oai_token-act-pair · gpt-3.5-turbo

references to annual awards and honors

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

bol

-0.82

esc

-0.79

agen

-0.74

actionDate

-0.73

idav

-0.72

duino

-0.72

apse

-0.69

ements

-0.68

paren

-0.68

kinson

-0.66

POSITIVE LOGITS

 honors

0.96

 Award

0.96

 contender

0.96

 awards

0.96

 Awards

0.91

Winner

0.87

 award

0.86

 finalists

0.82

 winner

0.79

 accol

0.77

Activations Density 0.035%

phrases related to awards or titles

references to annual awards and honors

No Comments

No Known Activations