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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pse

-0.83

 occas

-0.67

 numbered

-0.66

Shape

-0.66

 concess

-0.64

 interven

-0.63

 exception

-0.62

 Ambro

-0.61

akes

-0.60

igr

-0.60

POSITIVE LOGITS

selage

0.71

 Towns

0.71

ESC

0.69

 Avenger

0.67

 Braun

0.65

 Spears

0.64

ULAR

0.64

 centrif

0.63

riger

0.62

pez

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.