INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 horm

-0.72

 explor

-0.66

 prose

-0.63

arson

-0.62

 contrad

-0.60

natureconservancy

-0.60

 cann

-0.60

bleacher

-0.60

llan

-0.60

Interstitial

-0.59

POSITIVE LOGITS

heric

0.80

hetto

0.71

SI

0.70

yip

0.70

IE

0.63

imeter

0.63

 #####

0.61

atile

0.61

ichita

0.61

LM

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.