INDEX

Explanations

specific phrases enclosed in quotation marks

oai_token-act-pair · gpt-3.5-turbo

quotations or dialogue marks in the text

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

 challeng

-0.69

mitter

-0.65

jection

-0.64

mates

-0.63

 describ

-0.63

 puberty

-0.62

apon

-0.61

İĭ

-0.58

 rank

-0.58

ments

-0.58

POSITIVE LOGITS

/"

0.94

/>

0.75

kered

0.74

Stud

0.74

Elsa

0.73

Minecraft

0.70

["

0.70

mund

0.70

>>\

0.69

é¾į

0.69

Activations Density 0.066%

specific phrases enclosed in quotation marks

quotations or dialogue marks in the text

No Comments

No Known Activations