INDEX

Explanations

terms related to technology, businesses, organizations, and medical conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to specific films and media titles

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

ridden

-0.72

efully

-0.69

depending

-0.68

untled

-0.67

nown

-0.67

orically

-0.66

pause

-0.66

bably

-0.65

blown

-0.63

arently

-0.63

POSITIVE LOGITS

 Syndrome

0.78

 Disorder

0.72

 Association

0.71

 Disciple

0.67

 Contra

0.66

 guiName

0.66

âĦ¢:

0.65

 Practices

0.64

 Hail

0.64

 Radio

0.64

Activations Density 0.718%

terms related to technology, businesses, organizations, and medical conditions

terms related to specific films and media titles

No Comments

No Known Activations