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

ndra

-0.86

 Mysteries

-0.72

hler

-0.71

hn

-0.69

days

-0.68

hack

-0.66

hyde

-0.65

lease

-0.64

iatus

-0.64

azo

-0.64

POSITIVE LOGITS

emort

0.76

Sit

0.64

 quarters

0.62

 orders

0.61

 Burr

0.60

 Help

0.59

sic

0.59

 tender

0.58

 quarter

0.58

 floppy

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.