INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

CTR

-0.84

é¾įåĸļå£«

-0.75

 optic

-0.68

FG

-0.64

 Deaths

-0.63

 anat

-0.63

worthiness

-0.63

 Vision

-0.62

ac

-0.62

 optics

-0.61

POSITIVE LOGITS

aturday

0.87

ults

0.81

 Meier

0.73

iasco

0.70

 reckoning

0.69

ischer

0.68

aying

0.68

xtap

0.67

oling

0.67

ilan

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.