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

HIP

-0.73

cdn

-0.68

 mill

-0.67

isSpecialOrderable

-0.65

bil

-0.64

 headache

-0.63

tnc

-0.62

DOC

-0.62

 hungry

-0.62

 Wage

-0.61

POSITIVE LOGITS

etry

0.84

isexual

0.75

Row

0.73

creation

0.70

 Palest

0.70

Pav

0.68

seed

0.68

skirts

0.67

outing

0.66

Registered

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.