INDEX

Explanations

the word "all" followed by a hyphen and a descriptive adjective or noun

oai_token-act-pair · gpt-3.5-turbo

phrases containing the word "all" and contextually related concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

EStream

-0.84

KH

-0.73

hyde

-0.69

 Challenges

-0.68

 Puzzles

-0.65

ulty

-0.65

TeX

-0.64

ongyang

-0.64

awaru

-0.64

 Janeiro

-0.64

POSITIVE LOGITS

âĢĳ

0.79

0.77

auc

0.77

adic

0.76

usive

0.74

tackle

0.71

xious

0.71

ailable

0.69

ocratic

0.68

ctic

0.68

Activations Density 0.048%

the word "all" followed by a hyphen and a descriptive adjective or noun

phrases containing the word "all" and contextually related concepts

No Comments

No Known Activations