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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arnaev

-0.79

eret

-0.76

essee

-0.75

ombat

-0.74

%%%%

-0.74

emic

-0.71

lyak

-0.68

anta

-0.68

BOX

-0.68

kefeller

-0.67

POSITIVE LOGITS

 centrif

0.68

 Articles

0.61

 assures

0.59

 whereby

0.59

 intimid

0.59

 Random

0.59

 tion

0.58

 conve

0.58

 Indust

0.57

Random

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.