INDEX

Explanations

phrases expressing opinions, beliefs, or general statements

oai_token-act-pair · gpt-3.5-turbo

negations or phrases indicating what is not necessary or required

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¾įå¥ĳå£«

-0.67

 integrity

-0.62

 Forums

-0.62

 resumes

-0.61

 Adin

-0.60

 homosexuality

-0.58

 sincerity

-0.56

 affinity

-0.56

MpServer

-0.56

pires

-0.56

POSITIVE LOGITS

 yourselves

0.95

 yourself

0.94

 gotta

0.87

Tube

0.86

 need

0.85

 hear

0.82

plin

0.81

 expect

0.78

uld

0.78

 realise

0.77

Activations Density 0.176%

phrases expressing opinions, beliefs, or general statements

negations or phrases indicating what is not necessary or required

No Comments

No Known Activations