INDEX

Explanations

mentions of international treaties and negotiations

oai_token-act-pair · gpt-3.5-turbo

mentions of treaties and related legal terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

alach

-0.91

©¶æ

-0.79

edition

-0.72

gur

-0.71

serving

-0.71

stocks

-0.70

shown

-0.67

utenberg

-0.67

secut

-0.66

ĺħ

-0.64

POSITIVE LOGITS

 Treaty

1.09

 treaty

1.05

 treaties

0.97

 Agreement

0.87

breakers

0.86

ually

0.85

breaker

0.84

 stip

0.81

 Framework

0.78

 agreements

0.78

Activations Density 0.017%

mentions of international treaties and negotiations

mentions of treaties and related legal terms

No Comments

No Known Activations