INDEX

Explanations

names or terms related to legal and political matters

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to the name "Magnitsky."

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

OPLE

-0.84

ublic

-0.79

CHAT

-0.78

resp

-0.75

viously

-0.74

$$

-0.73

qq

-0.70

FAULT

-0.70

prototype

-0.68

rior

-0.68

POSITIVE LOGITS

ificent

1.28

olia

1.02

achev

0.95

 suspic

0.90

itude

0.90

 glim

0.88

animous

0.88

 satell

0.86

alez

0.85

istrates

0.84

Activations Density 0.009%

names or terms related to legal and political matters

proper nouns related to the name "Magnitsky."

No Comments

No Known Activations