INDEX

Explanations

phrases related to a high degree or intensity of something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "very" used to intensify descriptions

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

CHA

-0.71

 Chronicle

-0.58

 Redemption

-0.57

TION

-0.57

 Tempest

-0.57

tions

-0.56

 Rivals

-0.55

igi

-0.55

 Friendship

-0.54

 Crime

-0.54

POSITIVE LOGITS

 little

1.11

few

1.11

few

1.01

little

1.00

 large

0.96

 narrow

0.95

 stringent

0.95

 limited

0.95

low

0.94

 LIMITED

0.94

Activations Density 0.097%

phrases related to a high degree or intensity of something

instances of the word "very" used to intensify descriptions

No Comments

No Known Activations