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

Negative Logits

Downloadha

-0.79

unker

-0.77

arse

-0.73

aturdays

-0.69

inators

-0.68

 commute

-0.66

ilight

-0.66

erry

-0.65

irtual

-0.65

assin

-0.64

POSITIVE LOGITS

 floats

0.66

DOI

0.64

PID

0.63

acion

0.62

 Codes

0.62

 CODE

0.61

©¶æ¥µ

0.61

binding

0.61

ãĤ¼ãĤ¦ãĤ¹

0.60

uria

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.