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

seys

-0.78

ammers

-0.72

hands

-0.72

mur

-0.69

kers

-0.68

"]=>

-0.68

BUG

-0.67

IGH

-0.66

stals

-0.65

Kay

-0.65

POSITIVE LOGITS

lishes

0.68

acing

0.67

ictionary

0.66

 decree

0.63

 caution

0.62

 Dominion

0.61

 Cinderella

0.60

 awakening

0.59

ixed

0.59

 ballot

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.