INDEX

Explanations

the word "the" with a high activation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the."

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

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

anni

-0.80

lich

-0.78

-+-+

-0.78

ambo

-0.76

alde

-0.75

cade

-0.72

tu

-0.72

den

-0.71

alloc

-0.69

ploy

-0.68

POSITIVE LOGITS

 plunge

1.42

 brunt

1.31

 initiative

1.16

 bait

1.16

 reins

1.16

 opportunity

1.14

 helm

1.13

 liberty

1.13

 precaution

1.05

 leap

1.03

Activations Density 0.044%

the word "the" with a high activation

instances of the word "the."

No Comments

No Known Activations