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

ĸļ

-0.65

gra

-0.65

orter

-0.64

 posters

-0.64

illin

-0.63

lier

-0.63

culus

-0.63

 revolver

-0.61

oman

-0.61

 scissors

-0.59

POSITIVE LOGITS

 Rober

0.74

é¾įå

0.71

beta

0.70

dependent

0.65

 Adin

0.65

 guiActiveUnfocused

0.61

generic

0.60

equ

0.59

Pyr

0.59

 Depend

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.