INDEX

Explanations

phrases or terms related to a specific entity named "Pe"

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific character or persona represented by "Pe."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

schild

-0.96

IFIED

-0.76

 EDITION

-0.76

stretched

-0.76

EngineDebug

-0.75

orage

-0.74

naire

-0.73

selves

-0.73

 GOODMAN

-0.67

 Balanced

-0.67

POSITIVE LOGITS

anut

1.41

anuts

1.26

asant

1.19

eps

1.06

ggy

1.02

eper

1.02

eking

1.02

aky

1.02

ggie

1.01

ek

1.00

Activations Density 0.014%

phrases or terms related to a specific entity named "Pe"

mentions of a specific character or persona represented by "Pe."

No Comments

No Known Activations