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

ople

-0.68

bryce

-0.67

tty

-0.64

peak

-0.64

rise

-0.63

 Webs

-0.63

note

-0.61

bish

-0.61

ranch

-0.61

rice

-0.61

POSITIVE LOGITS

pired

0.89

pires

0.84

piring

0.79

par

0.71

 regards

0.71

 well

0.71

phy

0.69

ynchron

0.69

ipolar

0.68

 opposed

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.