INDEX

Explanations

verbs related to actions taken by individuals or groups

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Features by Cosine Similarity

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

Plots

Explanation

Show Test Field

Default Test Text

IFrame

Link

Not in Any Lists

Negative Logits

selves

-0.87

Higher

-0.74

 millenn

-0.71

 selves

-0.67

mint

-0.65

Versions

-0.65

%%

-0.65

aroo

-0.64

illion

-0.63

illions

-0.61

POSITIVE LOGITS

 herself

1.19

 himself

1.01

 adamant

0.76

her

0.75

 Himself

0.75

his

0.74

coy

0.71

 Tsarnaev

0.70

 arra

0.67

 hers

0.66

Activations Density 0.437%

verbs related to actions taken by individuals or groups

No Activations Uploaded