INDEX

Explanations

ranks or titles, especially military ranks like 'Colonel' and 'General'

oai_token-act-pair · gpt-3.5-turbo

titles and ranks associated with military personnel

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

âĹ¼

-0.76

 renters

-0.73

 Horses

-0.71

SourceFile

-0.68

Torrent

-0.68

Crash

-0.68

Sensor

-0.65

Score

-0.65

BRE

-0.65

âĶģ

-0.64

POSITIVE LOGITS

anamo

1.06

dinand

0.99

 Mattis

0.93

 Gaddafi

0.92

utenant

0.85

andum

0.85

 Eisenhower

0.82

apons

0.82

 Marshal

0.80

 stationed

0.79

Activations Density 0.041%

ranks or titles, especially military ranks like 'Colonel' and 'General'

titles and ranks associated with military personnel

No Comments

No Known Activations