INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

natureconservancy

-0.78

ANE

-0.70

 Autob

-0.69

amba

-0.67

itarian

-0.63

 ramifications

-0.63

 Robo

-0.63

 ordinances

-0.63

soType

-0.62

 earthqu

-0.62

POSITIVE LOGITS

Visual

0.77

Øª

0.74

oxide

0.70

chrome

0.69

visual

0.69

ÙĪ

0.68

ÙĦ

0.67

Ø§ÙĦ

0.67

tumblr

0.65

estic

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.