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

NetMessage

-0.70

FER

-0.69

inqu

-0.65

ilib

-0.65

fer

-0.64

ctions

-0.63

ibles

-0.63

uctor

-0.63

au

-0.62

 swayed

-0.62

POSITIVE LOGITS

aceae

0.86

 Reincarn

0.65

otin

0.62

 Wiggins

0.61

anium

0.61

Sphere

0.61

 Kasich

0.61

istics

0.61

okin

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.