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

è¦ļéĨĴ

-1.01

oco

-0.82

olls

-0.79

ãĤ¨ãĥ«

-0.73

orf

-0.71

aucas

-0.70

apan

-0.69

lin

-0.69

irth

-0.68

acial

-0.65

POSITIVE LOGITS

milo

0.67

ktop

0.67

 Deadline

0.63

 amps

0.62

 brightest

0.61

 Directive

0.60

AFTA

0.59

 wavelengths

0.58

anges

0.57

entry

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.