INDEX

Explanations

political and legal terms related to bans, regulations, and restrictions

oai_token-act-pair · gpt-3.5-turbo

references to political statements and legislation

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

ilogy

-0.81

 Brill

-0.73

oola

-0.71

 proverb

-0.67

 somew

-0.64

 Lauder

-0.64

 whirlwind

-0.63

JC

-0.62

library

-0.60

lopp

-0.59

POSITIVE LOGITS

 unlawful

0.87

icides

0.82

license

0.81

 violates

0.76

 lawfully

0.75

 activities

0.75

soever

0.74

 whatsoever

0.73

 offending

0.73

 solicitation

0.73

Activations Density 0.500%

political and legal terms related to bans, regulations, and restrictions

references to political statements and legislation

No Comments

No Known Activations