INDEX

Explanations

instances where a statement or phrase is followed by an elaboration or explanation

oai_token-act-pair · gpt-3.5-turbo

the phrase "that said," indicating transitions or qualifications in statements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

prus

-0.82

Desktop

-0.74

Bug

-0.72

Tai

-0.72

ItemImage

-0.71

 Tablet

-0.71

Feature

-0.69

Street

-0.69

MEN

-0.66

Jews

-0.64

POSITIVE LOGITS

sonian

0.79

itivity

0.66

 Blank

0.64

 goodbye

0.64

rescent

0.62

ickson

0.62

 anecd

0.60

 culmin

0.58

 intentions

0.56

 Cooke

0.56

Activations Density 0.058%

instances where a statement or phrase is followed by an elaboration or explanation

the phrase "that said," indicating transitions or qualifications in statements

No Known Activations