INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

eur

-0.74

milo

-0.72

went

-0.71

ģ«

-0.69

heid

-0.68

è¦ļéĨĴ

-0.67

ilion

-0.66

particip

-0.64

amazon

-0.63

Leod

-0.63

POSITIVE LOGITS

leep

0.72

Arcade

0.70

udos

0.65

reens

0.64

Battery

0.63

Lock

0.61

peria

0.60

*/(

0.59

Tok

0.58

 Skinner

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.