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

 Equality

-0.67

 Salary

-0.65

 divers

-0.65

 Networks

-0.65

 Commissioner

-0.64

ETH

-0.64

 Employees

-0.64

 Estate

-0.62

ADA

-0.61

DAV

-0.60

POSITIVE LOGITS

interstitial

0.87

slot

0.77

Mub

0.76

fulness

0.71

 IMAGES

0.70

stri

0.68

hops

0.68

Mp

0.68

rg

0.68

pees

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.