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

ADRA

-0.83

olkien

-0.71

 deliveries

-0.70

awaru

-0.69

 benefic

-0.69

esson

-0.69

anyl

-0.67

 ingred

-0.67

 resil

-0.67

espie

-0.66

POSITIVE LOGITS

flo

0.88

frog

0.77

mma

0.71

wolves

0.70

wom

0.68

pi

0.66

dream

0.64

mol

0.64

lights

0.62

da

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.