INDEX

Explanations

mentions of violent militant groups

oai_token-act-pair · gpt-3.5-turbo

references to militant groups or individuals associated with violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

nder

-0.75

 Gund

-0.74

bye

-0.69

MW

-0.69

itor

-0.68

 Wind

-0.68

pton

-0.66

upon

-0.65

 Meridian

-0.63

PT

-0.62

POSITIVE LOGITS

 militants

1.05

 gunmen

0.95

 insurgents

0.90

ervatives

0.89

 Islamists

0.85

 militant

0.85

ilitary

0.84

ervative

0.84

Enlarge

0.83

 gunman

0.83

Activations Density 0.008%

mentions of violent militant groups

references to militant groups or individuals associated with violence

No Comments

No Known Activations