INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

',

-0.78

sil

-0.71

Merit

-0.65

'.

-0.62

Pros

-0.59

âĢ¢âĢ¢âĢ¢âĢ¢

-0.59

 Kraken

-0.58

 adjourn

-0.57

âĹ¼

-0.57

 downfall

-0.57

POSITIVE LOGITS

bsite

0.77

alez

0.74

arnaev

0.71

ierrez

0.68

vez

0.67

abouts

0.66

idden

0.65

urrent

0.65

olin

0.64

nels

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.