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

material

-0.74

BSD

-0.71

 grounding

-0.71

theless

-0.66

MIS

-0.64

<?

-0.63

Untitled

-0.63

BIT

-0.60

visual

-0.60

viol

-0.59

POSITIVE LOGITS

anon

0.68

ular

0.68

icka

0.67

 villagers

0.66

endar

0.66

usher

0.65

onymous

0.64

umatic

0.63

lif

0.62

ulum

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.