INDEX

Explanations

No Explanations Found

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 redes

-0.88

ufact

-0.70

 recons

-0.67

ractor

-0.67

ESA

-0.66

CSI

-0.66

ega

-0.64

IPM

-0.63

essional

-0.63

 behest

-0.63

POSITIVE LOGITS

Ń·

0.68

imates

0.67

usha

0.65

åĳ

0.64

}}}

0.63

********************************

0.62

kies

0.61

 verbs

0.59

liv

0.59

ãĢ

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.