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

EngineDebug

-0.71

vertisements

-0.65

ovych

-0.64

ãĤ¢ãĥ«

-0.64

 Livingston

-0.62

 Rein

-0.61

 Nanto

-0.60

 Somerset

-0.60

oslav

-0.60

 Mold

-0.60

POSITIVE LOGITS

anche

0.69

 Controlled

0.68

osed

0.67

itated

0.65

iated

0.65

 Diaz

0.65

usted

0.64

 ejac

0.63

oder

0.63

itate

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.