INDEX

Explanations

personal pronouns and possessive pronouns referring to people around the subject

oai_token-act-pair · gpt-3.5-turbo

references to individuals and groups in relation to personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Geek

-0.73

rough

-0.70

âĢ¢âĢ¢

-0.68

ĻĤ

-0.66

ãĥ©ãĥ³

-0.65

 Pric

-0.65

-)

-0.63

 Majority

-0.63

Production

-0.61

ories

-0.61

POSITIVE LOGITS

atic

0.85

imei

0.77

 mate

0.76

atics

0.74

 conduc

0.73

 personally

0.72

ulkan

0.71

 selves

0.71

alian

0.69

soever

0.68

Activations Density 0.205%

personal pronouns and possessive pronouns referring to people around the subject

references to individuals and groups in relation to personal experiences

No Comments

No Known Activations