INDEX

Explanations

phrases indicating an underscored point or statement, potentially focusing on emphasizing something noteworthy or critical

oai_token-act-pair · gpt-3.5-turbo

phrases that express recommendations or obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vati

-0.66

ula

-0.62

select

-0.61

 proposes

-0.61

ses

-0.60

osa

-0.60

ulous

-0.60

 inconsist

-0.59

 chooses

-0.59

 uses

-0.57

POSITIVE LOGITS

 unsur

0.90

aan

0.78

 aston

0.77

ribune

0.75

 abundantly

0.75

 suffice

0.75

 horr

0.75

 surprise

0.74

 rejoice

0.74

antz

0.73

Activations Density 0.103%

phrases indicating an underscored point or statement, potentially focusing on emphasizing something noteworthy or critical

phrases that express recommendations or obligations

No Comments

No Known Activations