INDEX

Explanations

mentions of militant groups or individuals

oai_token-act-pair · gpt-3.5-turbo

references to militant groups or individuals involved in conflicts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

othy

-0.82

âĦ¢:

-0.78

ðĿ

-0.78

perature

-0.77

ORK

-0.77

IENCE

-0.77

encers

-0.76

velt

-0.73

 Revel

-0.72

ĳ

-0.71

POSITIVE LOGITS

 Islamist

0.90

 Islamists

0.90

 insurgency

0.85

 militant

0.82

 strongh

0.82

 insurg

0.82

 militants

0.79

Enlarge

0.78

 commanders

0.77

anamo

0.76

Activations Density 0.025%

mentions of militant groups or individuals

references to militant groups or individuals involved in conflicts

No Comments

No Known Activations