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

ufact

-0.84

iveness

-0.64

edom

-0.63

azeera

-0.63

 nostalg

-0.63

 Earthqu

-0.62

 wielded

-0.62

 monop

-0.58

Fn

-0.58

raints

-0.58

POSITIVE LOGITS

chwitz

0.76

Reviewer

0.70

gart

0.69

ogie

0.69

gard

0.67

Follow

0.66

ill

0.65

 Hayes

0.64

Same

0.64

rentices

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.