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

 dock

-0.69

asta

-0.65

Reward

-0.62

src

-0.61

 Surrey

-0.61

Opt

-0.61

 Cruise

-0.60

google

-0.59

Effects

-0.58

ATK

-0.58

POSITIVE LOGITS

ocally

0.80

teness

0.78

abor

0.69

wise

0.67

asionally

0.67

gently

0.66

urally

0.65

bern

0.64

ifice

0.63

atism

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.