INDEX

Explanations

mentions of law enforcement personnel and related activities

oai_token-act-pair · gpt-3.5-turbo

references to law enforcement and police terminology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Topics

-0.76

hani

-0.67

TPPStreamerBot

-0.67

 subsequ

-0.64

 livest

-0.64

gments

-0.64

 charism

-0.62

 Cambodia

-0.61

 pige

-0.61

anted

-0.60

POSITIVE LOGITS

 darn

0.84

creen

0.80

hers

0.80

hered

0.78

 pics

0.75

 jeans

0.74

aminer

0.74

 damned

0.73

zzle

0.73

 buddies

0.73

Activations Density 0.086%

mentions of law enforcement personnel and related activities

references to law enforcement and police terminology

No Comments

No Known Activations