INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

wark

-0.92

oult

-0.91

 pestic

-0.90

andals

-0.74

maxwell

-0.74

ODY

-0.72

cale

-0.71

upiter

-0.70

avez

-0.67

uyomi

-0.67

POSITIVE LOGITS

chu

0.67

 localization

0.64

jing

0.64

 project

0.63

 reflex

0.62

htt

0.62

Import

0.62

 overfl

0.61

Medium

0.61

bridge

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.