INDEX

Explanations

mentions of militant groups or military operations

oai_token-act-pair · gpt-3.5-turbo

terms related to militant groups and insurgencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

iture

-0.81

Consumer

-0.77

IENCE

-0.73

payer

-0.73

othy

-0.72

 Consumer

-0.72

 Dull

-0.72

 Goose

-0.71

 Circuit

-0.68

ilts

-0.68

POSITIVE LOGITS

 insurgents

1.14

 terrorists

1.05

 insurgency

1.01

 massac

0.98

 militants

0.98

 besie

0.98

 waging

0.97

 detonated

0.96

 infiltr

0.96

 jihadists

0.94

Activations Density 0.131%

mentions of militant groups or military operations

terms related to militant groups and insurgencies

No Comments

No Known Activations