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

xual

-0.73

 Krug

-0.72

 Debor

-0.69

chini

-0.66

mates

-0.63

Hai

-0.63

ó

-0.63

 flakes

-0.63

>]

-0.63

](

-0.63

POSITIVE LOGITS

braska

0.77

ersive

0.71

brance

0.71

miah

0.68

ensible

0.64

leground

0.64

 liberties

0.64

ream

0.64

Slot

0.63

ims

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.