INDEX

Explanations

phrases indicating personal opinions

oai_token-act-pair · gpt-3.5-turbo

phrases expressing personal views or opinions

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

llular

-0.69

 Himself

-0.64

raltar

-0.64

ULAR

-0.62

 Topic

-0.61

perty

-0.60

artney

-0.59

 Yourself

-0.59

 Weld

-0.59

Ton

-0.57

POSITIVE LOGITS

phas

0.74

 unres

0.69

owitz

0.68

sts

0.68

 terminating

0.60

 inval

0.59

 wrongful

0.58

opian

0.57

 affirmative

0.57

 aesthetic

0.56

Activations Density 0.038%

phrases indicating personal opinions

phrases expressing personal views or opinions

No Comments

No Known Activations