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

 wraps

-0.72

-0.63

ohm

-0.61

 Pistons

-0.60

 farewell

-0.60

 disappointment

-0.60

whel

-0.59

 misunder

-0.59

Sov

-0.59

 Nanto

-0.59

POSITIVE LOGITS

uthor

0.90

IAS

0.83

yip

0.80

icult

0.71

 Dism

0.68

ocations

0.66

overe

0.66

pse

0.65

usc

0.65

esian

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.