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

ModLoader

-0.74

schild

-0.71

çķ

-0.69

 Rebell

-0.69

ledged

-0.68

ccording

-0.67

inement

-0.65

 destro

-0.65

 Danger

-0.65

 undermin

-0.63

POSITIVE LOGITS

arily

0.73

ItemTracker

0.69

 Procedure

0.64

athi

0.63

pha

0.63

fits

0.62

outheastern

0.62

\":

0.59

angan

0.58

alam

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.