INDEX

Explanations

mentions of law enforcement officers or police activities

oai_token-act-pair · gpt-3.5-turbo

mentions of law enforcement officers in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DAY

-0.83

tera

-0.78

Shock

-0.75

FORE

-0.74

hered

-0.73

Tour

-0.71

imoto

-0.69

Deal

-0.69

izons

-0.69

_-

-0.66

POSITIVE LOGITS

 officers

1.10

 officer

1.02

 stationed

1.02

 patrolling

0.93

 Officers

0.89

utenant

0.84

paio

0.79

 corps

0.79

geant

0.77

 acad

0.75

Activations Density 0.030%

mentions of law enforcement officers or police activities

mentions of law enforcement officers in various contexts

No Comments

No Known Activations