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

juven

-0.81

ocaust

-0.76

ancock

-0.72

 Juven

-0.72

eree

-0.67

tera

-0.67

nir

-0.67

zynski

-0.66

jug

-0.66

Baz

-0.66

POSITIVE LOGITS

pci

0.74

 Spice

0.71

ãĥ¡

0.70

CLOSE

0.69

 Instr

0.68

Spoiler

0.66

 Vendor

0.64

GREEN

0.63

Catalog

0.62

 Yose

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.