INDEX

Explanations

information related to social media profiles and personal data

oai_token-act-pair · gpt-3.5-turbo

terms related to social media profiles and personal health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 ourselves

-0.80

 Rohing

-0.64

ichever

-0.63

 oneself

-0.62

 Helpful

-0.62

 THEIR

-0.61

VERTIS

-0.60

together

-0.60

aples

-0.59

Rober

-0.59

POSITIVE LOGITS

 wife

0.93

 buddies

0.84

 counterpart

0.82

 girlfriend

0.81

mates

0.81

 persona

0.81

panic

0.80

 superiors

0.79

 exploits

0.78

 subordinates

0.77

Activations Density 0.443%

information related to social media profiles and personal data

terms related to social media profiles and personal health

No Comments

No Known Activations