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

ucc

-0.98

endas

-0.86

egu

-0.82

enne

-0.81

anse

-0.79

rils

-0.79

ãĥĻ

-0.78

ern

-0.78

atan

-0.77

auldron

-0.76

POSITIVE LOGITS

 taxed

0.71

 trending

0.69

 Depend

0.67

 retire

0.67

stocks

0.64

 consequential

0.63

 Certified

0.62

 Married

0.62

 taxable

0.61

 Paid

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.