INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ertodd

-0.74

 Flavoring

-0.72

romy

-0.70

Newsletter

-0.68

UES

-0.63

-0.62

 sshd

-0.61

*/(

-0.61

amins

-0.60

 POST

-0.60

POSITIVE LOGITS

yrus

0.73

ore

0.70

ithing

0.68

abba

0.68

word

0.68

isSpecialOrderable

0.65

Unit

0.65

interstitial

0.64

alm

0.63

erness

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.