INDEX

Explanations

police departments (PD) or specific activities related to them

oai_token-act-pair · gpt-3.5-turbo

references to police department abbreviations and associations

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

hold

-0.76

ppo

-0.75

fee

-0.69

Sphere

-0.69

play

-0.67

Hug

-0.66

sett

-0.66

tem

-0.64

bda

-0.63

borough

-0.62

POSITIVE LOGITS

PD

0.90

ATES

0.84

illon

0.84

orate

0.80

ective

0.79

iamond

0.78

encies

0.77

ail

0.76

illard

0.74

 Constable

0.74

Activations Density 0.018%

police departments (PD) or specific activities related to them

references to police department abbreviations and associations

No Comments

No Known Activations