INDEX

Explanations

mentions of law enforcement agencies and legal terms

oai_token-act-pair · gpt-3.5-turbo

references to law enforcement or security agencies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ndra

-0.70

kun

-0.69

owan

-0.68

obyl

-0.68

jad

-0.68

amura

-0.66

hua

-0.66

 ç¥ŀ

-0.65

apest

-0.64

feat

-0.64

POSITIVE LOGITS

 commissioners

1.05

 Inspect

1.05

 officers

1.03

 Commissioner

1.03

 Inspector

0.98

 Officers

0.98

 commissioner

0.96

 inspector

0.95

 officer

0.94

 investigating

0.93

Activations Density 0.145%

mentions of law enforcement agencies and legal terms

references to law enforcement or security agencies

No Comments

No Known Activations