INDEX

Explanations

adjectives describing something as beneficial, practical, or advantageous

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otta

-0.65

 boarded

-0.65

uph

-0.64

 Alive

-0.62

agate

-0.61

buck

-0.61

Bom

-0.60

 Pall

-0.59

 Kard

-0.59

olition

-0.58

POSITIVE LOGITS

 idiots

1.16

 adjunct

0.83

 insights

0.81

 tools

0.80

tip

0.80

 insight

0.78

fully

0.78

 tool

0.76

tips

0.75

iences

0.72

Activations Density 0.048%

adjectives describing something as beneficial, practical, or advantageous

No Comments

No Known Activations