INDEX

Explanations

phrases related to law enforcement activities like raids

oai_token-act-pair · gpt-3.5-turbo

instances of the word "raided" and its variations indicating law enforcement actions

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

chell

-0.65

cong

-0.65

iovascular

-0.63

pure

-0.63

 Supplement

-0.62

puff

-0.61

minecraft

-0.61

 elevation

-0.60

Perfect

-0.60

rising

-0.59

POSITIVE LOGITS

 raided

0.99

 raids

0.92

 raid

0.89

nard

0.81

 spree

0.80

elled

0.79

 raiding

0.78

 sweeps

0.77

 seizure

0.75

itures

0.75

Activations Density 0.018%

phrases related to law enforcement activities like raids

instances of the word "raided" and its variations indicating law enforcement actions

No Comments

No Known Activations