INDEX

Explanations

phrases related to introductory statements indicating the beginning of an article or study

oai_token-act-pair · gpt-3.5-turbo

sections that introduce or pose a discussion on a specific topic or article

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

scribe

-0.71

 Others

-0.66

iously

-0.61

inately

-0.61

ulz

-0.59

grain

-0.59

fine

-0.59

Cover

-0.59

unt

-0.58

ocry

-0.57

POSITIVE LOGITS

 however

1.04

 moreover

0.80

 though

0.65

 meanwhile

0.64

 Carlo

0.64

 there

0.64

 wherein

0.63

we

0.62

 Ichigo

0.62

there

0.61

Activations Density 0.259%

phrases related to introductory statements indicating the beginning of an article or study

sections that introduce or pose a discussion on a specific topic or article

No Comments

No Known Activations