INDEX

Explanations

references to awards or recognitions

oai_token-act-pair · gpt-3.5-turbo

references to sports awards and their corresponding years

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

bol

-0.80

hett

-0.78

dor

-0.75

idav

-0.75

ements

-0.74

sett

-0.71

fram

-0.71

actionDate

-0.71

ersen

-0.69

bent

-0.68

POSITIVE LOGITS

 honors

0.85

 awards

0.82

 Awards

0.79

 Sabha

0.78

 award

0.76

 Award

0.76

 contender

0.76

âĦ¢

0.72

GHz

0.68

Winner

0.67

Activations Density 0.066%

references to awards or recognitions

references to sports awards and their corresponding years

No Comments

No Known Activations