INDEX

Explanations

references to the Islamic State terrorist group

oai_token-act-pair · gpt-3.5-turbo

references to the Islamic State group and its activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

oard

-0.79

Wheel

-0.76

ezvous

-0.72

Consumer

-0.72

uckland

-0.71

othy

-0.70

Seattle

-0.69

itures

-0.69

park

-0.69

iture

-0.67

POSITIVE LOGITS

 militants

1.33

 militant

1.20

 insurgents

1.19

 insurgency

1.15

 jihadists

1.15

 jihadist

1.14

 fighters

1.12

 terrorists

1.09

 extremists

1.06

 terrorist

1.04

Activations Density 0.028%

references to the Islamic State terrorist group

references to the Islamic State group and its activities

No Comments

No Known Activations