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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oldown

-0.85

 horizont

-0.70

pull

-0.68

origin

-0.67

pse

-0.67

 showc

-0.65

quo

-0.65

 telesc

-0.65

 contribut

-0.64

ibus

-0.64

POSITIVE LOGITS

Studio

0.69

ificial

0.68

î

0.67

 Palm

0.66

 Prepar

0.65

iano

0.65

NBA

0.64

atic

0.63

atile

0.63

 Birds

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.