INDEX

Explanations

terms related to intelligence and the intelligence community

oai_token-act-pair · gpt-3.5-turbo

references to intelligence and intelligence agencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

nered

-0.81

pain

-0.80

cair

-0.69

zl

-0.69

thur

-0.67

dule

-0.65

witz

-0.64

orld

-0.63

Benz

-0.62

iless

-0.62

POSITIVE LOGITS

 briefings

1.06

 agencies

0.97

 gathering

0.94

 Agency

0.90

 briefing

0.85

agency

0.84

 agency

0.83

 operatives

0.83

 dossier

0.79

elligence

0.79

Activations Density 0.031%

terms related to intelligence and the intelligence community

references to intelligence and intelligence agencies

No Comments

No Known Activations