INDEX

Explanations

the word "Hi" in various contexts

oai_token-act-pair · gpt-3.5-turbo

greetings or variations of "hi."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å£«

-0.87

 Awakens

-0.85

*/(

-0.79

 rall

-0.69

lain

-0.69

Dialogue

-0.67

parts

-0.65

å¥³

-0.65

 destro

-0.64

 Gleaming

-0.64

POSITIVE LOGITS

earch

0.97

Fi

0.88

pped

0.81

pping

0.80

dden

0.79

roy

0.75

Bs

0.73

ya

0.72

kson

0.72

ature

0.71

Activations Density 0.015%

the word "Hi" in various contexts

greetings or variations of "hi."

No Comments

No Known Activations