INDEX

Explanations

phrases related to leadership and authority

oai_token-act-pair · gpt-3.5-turbo

language related to political accountability and governance

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Krypt

-0.70

yz

-0.69

çķ

-0.68

ONSORED

-0.68

 Bolt

-0.67

Origin

-0.67

 neighbour

-0.66

Vel

-0.65

Bub

-0.65

onement

-0.63

POSITIVE LOGITS

 salaries

1.02

 vested

0.98

 discretion

0.98

 oversee

0.97

 themselves

0.92

 resigned

0.90

 routinely

0.84

cius

0.83

 desks

0.83

 overseeing

0.83

Activations Density 0.763%

phrases related to leadership and authority

language related to political accountability and governance

No Comments

No Known Activations