INDEX

Explanations

intense or extreme descriptions or statements

oai_token-act-pair · gpt-3.5-turbo

the concept of "crazy" or extreme behavior and situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Reviewed

-0.98

tein

-0.87

ribut

-0.83

ribute

-0.83

âĢ¢âĢ¢âĢ¢âĢ¢

-0.78

 Cheong

-0.78

lain

-0.70

apers

-0.69

AUT

-0.68

arers

-0.68

POSITIVE LOGITS

 crazy

0.89

 nuts

0.82

 insane

0.74

 chic

0.72

 overboard

0.71

 insanity

0.69

crazy

0.69

 darling

0.69

 beasts

0.69

ishly

0.67

Activations Density 0.011%

intense or extreme descriptions or statements

the concept of "crazy" or extreme behavior and situations

No Comments

No Known Activations