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

eers

-0.73

gettable

-0.73

rieve

-0.67

 Ryder

-0.63

 Bhar

-0.63

aired

-0.62

 yourselves

-0.59

fecture

-0.59

fit

-0.58

cele

-0.57

POSITIVE LOGITS

eno

0.76

Weather

0.72

intage

0.71

0.70

ague

0.70

OUN

0.70

 Historical

0.67

 Extensions

0.65

 multiplication

0.65

fields

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.