INDEX

Explanations

text related to political figures and actions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Moore

-0.97

heed

-0.83

Kaw

-0.78

awa

-0.76

Oak

-0.76

ayne

-0.75

 Booker

-0.74

 McKenzie

-0.74

NRL

-0.74

Carter

-0.74

POSITIVE LOGITS

 Hungary

2.43

 Budapest

2.41

 Hungarian

2.39

Hung

2.08

 Hung

2.02

 Romania

1.91

 Romanian

1.84

 Slovakia

1.77

 Bulgar

1.72

 Viktor

1.68

Activations Density 0.178%

text related to political figures and actions

No Comments

No Known Activations