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

 ÏĦ

-0.71

XD

-0.67

ãĥ¼ãĥĨ

-0.66

 writ

-0.65

 Dome

-0.64

writ

-0.64

é¾įå

-0.64

spir

-0.62

lite

-0.62

theless

-0.60

POSITIVE LOGITS

ogie

0.75

OHN

0.73

adelphia

0.72

aceae

0.71

akespeare

0.69

opus

0.68

ategory

0.67

 orchestra

0.65

Native

0.64

INFO

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.