INDEX

Explanations

instances where something is being controlled or influenced by an authoritative force

oai_token-act-pair · gpt-3.5-turbo

words related to control or authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

swick

-0.75

este

-0.72

Tok

-0.71

att

-0.69

Hat

-0.69

Dak

-0.69

 Charity

-0.69

Mary

-0.67

 Fighting

-0.67

 Horn

-0.66

POSITIVE LOGITS

 dictated

1.48

 dictate

1.35

 dictates

1.26

 confir

1.12

 dict

0.93

rul

0.83

 governs

0.83

 lapt

0.81

 corrid

0.81

é¾įå¥ĳå£«

0.79

Activations Density 0.013%

instances where something is being controlled or influenced by an authoritative force

words related to control or authority

No Comments

No Known Activations