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

ters

-0.70

 Swed

-0.68

lists

-0.68

ãĤ¼

-0.66

DonaldTrump

-0.64

worm

-0.63

 Scal

-0.61

 Collect

-0.61

 dict

-0.60

Erd

-0.59

POSITIVE LOGITS

arij

0.74

inness

0.71

INESS

0.70

acterial

0.68

jri

0.66

vette

0.65

actual

0.64

capacity

0.64

awei

0.63

kefeller

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.