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

iatric

-0.72

GD

-0.66

PT

-0.65

ologically

-0.63

 comparisons

-0.62

opathy

-0.61

 indications

-0.60

opath

-0.60

Īè

-0.59

 Lars

-0.58

POSITIVE LOGITS

ividual

0.95

wick

0.68

blade

0.67

olulu

0.67

ety

0.66

cation

0.64

onies

0.63

 blot

0.61

iolet

0.61

aday

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.