INDEX

Explanations

references to awards or recognition

oai_token-act-pair · gpt-3.5-turbo

references to awards and recognitions

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

ierre

-0.75

ohyd

-0.68

Geo

-0.68

ths

-0.65

ford

-0.63

vironment

-0.63

 Breat

-0.63

 Archangel

-0.62

 Ange

-0.62

 Steps

-0.62

POSITIVE LOGITS

 laure

1.00

 awards

0.98

 awarded

0.97

 winner

0.93

 prizes

0.90

 winners

0.89

 nominations

0.89

 bestowed

0.89

Winner

0.88

 awarding

0.86

Activations Density 0.028%

references to awards or recognition

references to awards and recognitions

No Comments

No Known Activations