INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 sergeant

-0.64

ierrez

-0.64

ariat

-0.63

//[

-0.62

 timestamp

-0.62

KGB

-0.62

 fastball

-0.61

 extradition

-0.61

 è£ıè¦ļéĨĴ

-0.61

tee

-0.61

POSITIVE LOGITS

Netflix

0.81

venants

0.81

Haw

0.77

ngth

0.75

ipel

0.72

Edited

0.71

ogie

0.70

olulu

0.70

ingu

0.69

mith

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.