INDEX

Explanations

phrases containing the word "less."

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

elia

-0.81

NEWS

-0.78

munition

-0.76

BAT

-0.76

BU

-0.74

issues

-0.70

BIT

-0.68

mint

-0.68

èª

-0.67

FLAG

-0.67

POSITIVE LOGITS

edly

0.74

 autom

0.72

ieu

0.72

nesses

0.70

lihood

0.67

zhen

0.65

 Ones

0.65

terday

0.64

soever

0.63

erness

0.63

Activations Density 0.061%

phrases containing the word "less."

No Comments

No Known Activations