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

cery

-0.72

tnc

-0.70

 Stamp

-0.69

Paw

-0.68

format

-0.67

recy

-0.67

float

-0.63

ALLY

-0.63

 Cele

-0.62

mt

-0.62

POSITIVE LOGITS

aeda

0.84

 endured

0.65

olition

0.64

 subdu

0.64

 bomber

0.63

 prof

0.62

 belts

0.62

akia

0.61

 bridges

0.61

 choke

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.