INDEX

Explanations

phrases related to involvement or participation

oai_token-act-pair · gpt-3.5-turbo

the word "involve" and its variations, as well as the concept of belonging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

was

-0.74

was

-0.71

Was

-0.69

is

-0.67

 heads

-0.62

 wasn

-0.61

Has

-0.60

 hasn

-0.59

Was

-0.57

isn

-0.57

POSITIVE LOGITS

 involve

1.95

 originate

1.66

 imply

1.65

 constitute

1.65

 signify

1.63

 rely

1.60

 require

1.59

 resemble

1.59

 denote

1.59

 violate

1.56

Activations Density 0.069%

phrases related to involvement or participation

the word "involve" and its variations, as well as the concept of belonging

No Comments

No Known Activations