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

 ancest

-0.76

 Emerson

-0.75

 Invention

-0.69

izable

-0.68

efined

-0.63

resents

-0.63

neau

-0.63

 Colleg

-0.63

umbn

-0.62

amaz

-0.61

POSITIVE LOGITS

wcsstore

0.96

USD

0.74

actionDate

0.72

IVERS

0.69

apers

0.68

owe

0.65

++++++++++++++++

0.63

andre

0.63

utils

0.63

ween

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.