INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ecast

-0.74

olars

-0.74

hao

-0.73

apter

-0.72

Hispanic

-0.72

osta

-0.70

iatus

-0.68

aucas

-0.67

elong

-0.66

ni

-0.64

POSITIVE LOGITS

 Philipp

0.72

projects

0.70

mble

0.68

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.67

 Stard

0.67

ãĥķãĤ©

0.66

=]

0.65

 Lovely

0.65

ãĥķãĤ¡

0.63

krit

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.