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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ramid

-0.76

Reviewer

-0.74

dot

-0.71

nep

-0.71

ilo

-0.69

 Noir

-0.69

icter

-0.68

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

-0.67

inqu

-0.66

ften

-0.66

POSITIVE LOGITS

iewicz

0.84

andowski

0.71

arthed

0.70

imov

0.64

mia

0.63

ansson

0.62

 Audi

0.62

Muk

0.61

 Patriarch

0.60

ansk

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.