INDEX

Explanations

references to prisoners or captivity

oai_token-act-pair · gpt-3.5-turbo

terms related to prisoners of war

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

orp

-0.79

 Boll

-0.76

orie

-0.71

laus

-0.65

wig

-0.65

ulously

-0.64

OPA

-0.63

alore

-0.62

ripp

-0.62

amera

-0.62

POSITIVE LOGITS

 prisoners

1.05

 captives

0.91

 inmates

0.88

 prisoner

0.85

 sentenced

0.81

 detainees

0.80

 incarcerated

0.75

icts

0.74

 jailed

0.73

 hostages

0.73

Activations Density 0.034%

references to prisoners or captivity

terms related to prisoners of war

No Comments

No Known Activations