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

 clearing

-0.73

 preaching

-0.70

 atro

-0.64

 looting

-0.64

 appropriation

-0.62

 giving

-0.62

 dragging

-0.61

 starving

-0.61

 gospel

-0.61

 killing

-0.60

POSITIVE LOGITS

ollo

0.84

sbm

0.82

Ã§

0.74

quer

0.74

)</

0.73

istas

0.73

Reviewer

0.73

appropriately

0.70

ISO

0.70

Intern

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.