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

wake

-0.90

peak

-0.68

wip

-0.65

prime

-0.64

tones

-0.63

ĸļ

-0.63

Sag

-0.62

 swipe

-0.62

lda

-0.59

 sear

-0.59

POSITIVE LOGITS

 consensual

0.67

MpServer

0.67

elman

0.64

AAF

0.64

ane

0.63

asca

0.61

ordable

0.60

assadors

0.59

dj

0.59

azar

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.