INDEX

Explanations

mentions or references to law enforcement entities

oai_token-act-pair · gpt-3.5-turbo

references to law enforcement and its activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

yip

-0.92

thur

-0.88

urn

-0.87

cair

-0.84

ranged

-0.82

hift

-0.79

amaz

-0.78

pread

-0.75

blank

-0.75

isted

-0.75

POSITIVE LOGITS

 agencies

1.37

 personnel

1.11

 officials

1.10

 officers

1.08

 agency

1.07

 officer

1.07

 authorities

1.02

 agents

0.94

 professionals

0.92

 Officials

0.91

Activations Density 0.037%

mentions or references to law enforcement entities

references to law enforcement and its activities

No Comments

No Known Activations