INDEX

Explanations

terms related to political figures' names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, including names and specific identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

APS

-0.85

sa

-0.85

transform

-0.84

 sidx

-0.83

ãĥĺãĥ©

-0.77

srf

-0.76

SAP

-0.75

 âī

-0.74

 scient

-0.73

 Imag

-0.73

POSITIVE LOGITS

ley

1.46

LEY

1.24

leys

1.12

lay

1.03

lee

0.96

sey

0.95

cliffe

0.92

leton

0.90

 Payton

0.90

 Bentley

0.89

Activations Density 0.190%

terms related to political figures' names

proper nouns, including names and specific identifiers

No Comments

No Known Activations