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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ĥİ

-0.79

ax

-0.68

 stakes

-0.64

 Petra

-0.63

ĪĴ

-0.61

dar

-0.61

aretz

-0.61

alpha

-0.60

Msg

-0.60

 altar

-0.60

POSITIVE LOGITS

orrow

0.70

 shenan

0.70

atile

0.69

 subscribe

0.69

undown

0.67

 Stories

0.66

ust

0.66

Track

0.65

interstitial

0.65

ousand

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.