INDEX

Explanations

references to the historical figure "Zeppelin"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Zeppelin."

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

Not in Any Lists

No Comments

Negative Logits

Interstitial

-0.78

ainers

-0.78

wear

-0.74

DOWN

-0.69

yrinth

-0.68

ainment

-0.66

sburgh

-0.65

 CLIENT

-0.64

ãģį

-0.64

ships

-0.64

POSITIVE LOGITS

ppelin

1.17

itsch

0.99

lda

0.98

Ze

0.95

eker

0.88

iger

0.86

plin

0.85

usha

0.85

ben

0.84

ichen

0.84

Activations Density 0.014%

references to the historical figure "Zeppelin"

references to the term "Zeppelin."

No Comments

No Known Activations