INDEX

Explanations

phrases related to sharing or commonalities

oai_token-act-pair · gpt-3.5-turbo

expressions related to sharing or commonalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

paio

-0.79

ģĸ

-0.74

Ī

-0.74

wagen

-0.73

steen

-0.73

¨

-0.73

ª

-0.72

¹

-0.71

 looph

-0.70

¿½

-0.70

POSITIVE LOGITS

edin

0.94

 secrets

0.83

 platform

0.75

 shares

0.71

 surname

0.70

 workspace

0.69

 share

0.69

eeds

0.69

onym

0.68

 plot

0.68

Activations Density 0.143%

phrases related to sharing or commonalities

expressions related to sharing or commonalities

No Comments

No Known Activations