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

ancies

-0.84

mberg

-0.81

miah

-0.78

ilib

-0.74

hetti

-0.70

ilia

-0.70

ornia

-0.69

henko

-0.69

uana

-0.69

urat

-0.68

POSITIVE LOGITS

SPONSORED

0.74

 advoc

0.68

 wisdom

0.65

RPG

0.64

omics

0.63

none

0.62

Desktop

0.62

 relent

0.61

 yours

0.60

 obscurity

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.