INDEX

Explanations

series of characters representing a pause or ellipsis, indicating a break in the text or speech

oai_token-act-pair · gpt-3.5-turbo

ellipses indicating omitted text or pauses in discourse

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

 Lama

-0.72

eday

-0.67

 Seym

-0.67

 grate

-0.66

 destro

-0.66

estyles

-0.65

arnaev

-0.64

mares

-0.63

 mathemat

-0.63

 ported

-0.62

POSITIVE LOGITS

future

0.79

their

0.79

demand

0.76

traditional

0.76

another

0.75

those

0.75

specified

0.73

them

0.72

existing

0.71

certain

0.70

Activations Density 0.242%

series of characters representing a pause or ellipsis, indicating a break in the text or speech

ellipses indicating omitted text or pauses in discourse

No Comments

No Known Activations