INDEX

Explanations

terms related to law enforcement and police work

oai_token-act-pair · gpt-3.5-turbo

terms related to policing and law enforcement

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

stream

-0.88

topic

-0.87

opian

-0.85

hus

-0.83

lund

-0.82

thumbnails

-0.82

jri

-0.79

mining

-0.78

rator

-0.77

range

-0.77

POSITIVE LOGITS

 guarding

0.79

 blot

0.78

 stationed

0.76

 patrolling

0.76

 enforcing

0.75

 Detect

0.74

 crackdown

0.70

 NYPD

0.69

 enforcement

0.69

 narcotics

0.69

Activations Density 0.052%

terms related to law enforcement and police work

terms related to policing and law enforcement

No Comments

No Known Activations