INDEX

Explanations

references to a specific physical barrier intended to separate geographical areas

oai_token-act-pair · gpt-3.5-turbo

references to a border wall and related topics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-0.81

Lear

-0.75

Temp

-0.75

ÃĽ

-0.73

çĶ°

-0.72

OTAL

-0.72

uner

-0.71

Dist

-0.70

Sym

-0.70

Ju

-0.68

POSITIVE LOGITS

 amnesty

0.84

 tightening

0.83

 roundup

0.80

 treaties

0.79

 rigged

0.78

 ramps

0.78

 wars

0.78

 militar

0.77

 creep

0.76

 swaps

0.76

Activations Density 0.205%

references to a specific physical barrier intended to separate geographical areas

references to a border wall and related topics

No Comments

No Known Activations