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

hyde

-0.76

 leveled

-0.68

 waged

-0.66

pires

-0.64

 toler

-0.63

oshenko

-0.62

 Nightmare

-0.61

Ore

-0.60

 nause

-0.60

ese

-0.59

POSITIVE LOGITS

ãĤ¸

0.74

 è£ıè¦ļéĨĴ

0.72

ãĥĩãĤ£

0.69

rities

0.68

=#

0.68

iously

0.68

ãĥ¼ãĥ«

0.68

 Âł Âł Âł Âł Âł Âł Âł Âł

0.67

ãĤ®

0.66

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.