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

 TRUMP

-0.71

ebin

-0.65

natureconservancy

-0.62

DOI

-0.62

 Supplement

-0.62

 custody

-0.62

anian

-0.61

 hust

-0.61

rero

-0.61

 verb

-0.60

POSITIVE LOGITS

mage

0.90

pointers

0.73

ilaterally

0.72

monton

0.72

hower

0.68

HAM

0.66

DEN

0.65

our

0.64

inburgh

0.64

ieu

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.