INDEX

Explanations

phrases related to personal qualities or characteristics

oai_token-act-pair · gpt-3.5-turbo

negative traits and behaviors associated with individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Photos

-0.72

 cancell

-0.65

 guiName

-0.64

 Authors

-0.63

Che

-0.62

hern

-0.60

wake

-0.59

Grab

-0.58

ocking

-0.58

 Manufacturer

-0.57

POSITIVE LOGITS

 himself

0.77

 passionately

0.73

 lived

0.72

 genuinely

0.69

 herself

0.69

 fluent

0.68

 perpetually

0.68

 tirelessly

0.66

 kindly

0.66

ufact

0.64

Activations Density 0.341%

phrases related to personal qualities or characteristics

negative traits and behaviors associated with individuals

No Comments

No Known Activations