INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

è¦ļéĨĴ

-0.87

RESULTS

-0.84

EStreamFrame

-0.81

ãĢı

-0.78

wikipedia

-0.70

published

-0.69

EStream

-0.67

travel

-0.67

tein

-0.67

åİ

-0.66

POSITIVE LOGITS

 Bhar

0.77

 Shim

0.70

 Sylv

0.69

istries

0.69

Tel

0.68

 Shiv

0.68

Som

0.67

ylum

0.67

 Vinyl

0.67

 limbo

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.