INDEX

Explanations

words related to the material "cement."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "cement" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

lihood

-0.78

finder

-0.73

————————

-0.67

option

-0.63

arenthood

-0.62

izons

-0.61

 WRITE

-0.60

 nerv

-0.59

RESULTS

-0.59

 uninsured

-0.59

POSITIVE LOGITS

 cement

1.29

urated

0.80

itious

0.79

ified

0.76

 seal

0.76

ed

0.75

ements

0.75

crete

0.75

 resin

0.73

ing

0.72

Activations Density 0.007%

words related to the material "cement."

instances of the word "cement" and its variations

No Comments

No Known Activations