INDEX

Explanations

references to different police departments

oai_token-act-pair · gpt-3.5-turbo

mentions of police departments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

term

-0.75

figure

-0.72

ties

-0.71

sed

-0.68

ted

-0.68

table

-0.68

clusions

-0.68

piring

-0.67

ãĤ¦

-0.66

sett

-0.65

POSITIVE LOGITS

 brass

0.84

 superintendent

0.78

abulary

0.77

 Department

0.75

 paramed

0.74

 fielded

0.74

 SWAT

0.73

 Superintendent

0.71

OA

0.71

 personnel

0.71

Activations Density 0.050%

references to different police departments

mentions of police departments

No Comments

No Known Activations