INDEX

Explanations

words related to personal statements or confessions

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating relationships or connections between subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 adolesc

-0.70

OUGH

-0.66

OPLE

-0.64

ORN

-0.62

 elusive

-0.60

 funer

-0.59

 homelessness

-0.59

agos

-0.59

 adultery

-0.58

CRIP

-0.58

POSITIVE LOGITS

stood

0.81

felt

0.77

lived

0.77

might

0.71

should

0.69

won

0.67

earned

0.66

shall

0.65

essed

0.64

ould

0.63

Activations Density 0.147%

words related to personal statements or confessions

conjunctions and phrases indicating relationships or connections between subjects

No Comments

No Known Activations