INDEX

Explanations

instances where something is being emphasized or pointed out

oai_token-act-pair · gpt-3.5-turbo

phrases that suggest causality or connection between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ramids

-0.68

uku

-0.66

bill

-0.65

mill

-0.65

eer

-0.61

Cub

-0.60

jury

-0.59

Family

-0.59

ione

-0.59

case

-0.58

POSITIVE LOGITS

 mattered

0.91

rouse

0.89

 distinguishes

0.85

 bothers

0.83

 prompted

0.80

 determines

0.79

 drew

0.75

 attracts

0.75

 inspires

0.74

ozy

0.74

Activations Density 0.119%

instances where something is being emphasized or pointed out

phrases that suggest causality or connection between concepts

No Comments

No Known Activations