INDEX

Explanations

No Explanations Found

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itizens

-0.71

stall

-0.67

uton

-0.65

veland

-0.64

DERR

-0.63

ktop

-0.61

alist

-0.61

nect

-0.61

essional

-0.60

 cater

-0.60

POSITIVE LOGITS

osponsors

0.69

DragonMagazine

0.69

ĸļ

0.68

exclusive

0.67

ospons

0.64

ecd

0.60

ski

0.60

Zip

0.59

>:

0.58

STE

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.