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

Scroll

-0.77

kered

-0.75

avior

-0.73

hess

-0.71

oun

-0.71

eeper

-0.71

keye

-0.71

rave

-0.70

atche

-0.70

 largeDownload

-0.69

POSITIVE LOGITS

ariat

0.72

Osw

0.71

 undertaking

0.64

 outpost

0.63

ATIVE

0.63

 beams

0.61

 salaries

0.61

 Kinnikuman

0.60

ord

0.59

mony

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.