INDEX

Explanations

references to Islamic extremist groups or military actions.

oai_token-act-pair · gpt-3.5-turbo

mentions of specific groups or factions in a conflict context

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

âĢ¢âĢ¢âĢ¢âĢ¢

-0.70

 Edison

-0.69

 Scotch

-0.68

Minecraft

-0.67

elong

-0.66

PAX

-0.65

iker

-0.64

ipeg

-0.64

 Debt

-0.63

 Robo

-0.62

POSITIVE LOGITS

usra

1.03

Nusra

0.93

 Front

0.91

 Idlib

0.87

Syrian

0.86

 rebels

0.86

 fighters

0.83

Sham

0.83

 fronts

0.79

 Aleppo

0.77

Activations Density 0.023%

references to Islamic extremist groups or military actions.

mentions of specific groups or factions in a conflict context

No Comments

No Known Activations