INDEX

Explanations

terms related to leadership or authority

oai_token-act-pair · gpt-3.5-turbo

references to roles, responsibilities, and structures related to governance and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Sorce

-0.63

bably

-0.63

lication

-0.60

Pok

-0.59

arnaev

-0.58

repre

-0.58

ivably

-0.55

Accessory

-0.54

 respondents

-0.53

ãĥ¯ãĥ³

-0.52

POSITIVE LOGITS

",

1.98

"?

1.94

"]

1.89

".

1.89

";

1.80

")

1.78

"—

1.76

"!

1.75

").

1.75

"...

1.73

Activations Density 0.519%

terms related to leadership or authority

references to roles, responsibilities, and structures related to governance and technology

No Comments

No Known Activations