INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

McA

-0.93

iard

-0.74

quire

-0.70

 Vander

-0.69

ffee

-0.68

 BASE

-0.67

hran

-0.67

JO

-0.64

cv

-0.64

IUM

-0.63

POSITIVE LOGITS

essions

0.80

iliated

0.79

yip

0.66

ornia

0.66

rawdownloadcloneembedreportprint

0.63

 tools

0.62

 Pastebin

0.62

 pill

0.62

fml

0.61

 disillusion

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.