INDEX

Explanations

information related to the detention center at Guantanamo Bay

oai_token-act-pair · gpt-3.5-turbo

references to Guantanamo Bay and related topics

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

WN

-0.79

 Franch

-0.77

Merit

-0.77

 Pixie

-0.74

theless

-0.72

Offline

-0.71

drive

-0.66

hy

-0.66

bye

-0.64

iren

-0.64

POSITIVE LOGITS

anamo

1.20

 Guantanamo

1.15

 Guant

1.09

 detainees

1.08

 detainee

0.94

 detention

0.93

 Hussein

0.92

 captives

0.86

 confinement

0.84

 prisoners

0.83

Activations Density 0.020%

information related to the detention center at Guantanamo Bay

references to Guantanamo Bay and related topics

No Comments

No Known Activations