INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Wo

-0.93

 juven

-0.75

Temperature

-0.73

Role

-0.70

GN

-0.70

Sleep

-0.65

GN

-0.64

Boot

-0.63

desktop

-0.62

leep

-0.60

POSITIVE LOGITS

arov

0.96

ierrez

0.78

henko

0.75

aukee

0.74

orney

0.72

ucha

0.70

llah

0.67

atl

0.67

 Lauder

0.66

urdue

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.