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

entin

-0.71

urst

-0.69

enance

-0.64

 quarry

-0.63

stock

-0.62

bern

-0.61

ixt

-0.61

 warehouse

-0.60

 Weston

-0.59

dan

-0.59

POSITIVE LOGITS

BILITIES

0.90

Ń·

0.88

interstitial

0.86

Ú

0.79

inen

0.78

andem

0.74

eus

0.69

ãĤ§

0.68

ramid

0.67

ength

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.