INDEX

Explanations

keywords related to organizational or sequential information, such as "Next" or chapters

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Next" indicating a transition or continuation in text

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

 Feldman

-0.77

 Sinai

-0.74

 Erie

-0.66

ini

-0.65

 Ãĸ

-0.65

 chests

-0.64

icone

-0.64

 Legions

-0.62

lees

-0.62

 Rossi

-0.60

POSITIVE LOGITS

 Generations

0.78

STEP

0.77

door

0.76

 generation

0.76

olicy

0.75

ĻĤ

0.75

 generations

0.74

 Steps

0.73

 installment

0.71

 iteration

0.70

Activations Density 0.043%

keywords related to organizational or sequential information, such as "Next" or chapters

instances of the word "Next" indicating a transition or continuation in text

No Comments

No Known Activations