INDEX

Explanations

mentions of the militant group "Hamas."

oai_token-act-pair · gpt-3.5-turbo

mentions of the group Hamas

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aunder

-0.80

raught

-0.75

mson

-0.69

ttes

-0.68

ŃĶ

-0.67

 oats

-0.66

 Scotch

-0.66

 Fargo

-0.65

 LAPD

-0.64

ouver

-0.64

POSITIVE LOGITS

abad

0.81

etz

0.81

 militants

0.80

 operatives

0.78

 insurgents

0.77

 militant

0.77

abi

0.76

 extremists

0.74

 Hamas

0.73

anca

0.73

Activations Density 0.010%

mentions of the militant group "Hamas."

mentions of the group Hamas

No Comments

No Known Activations