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

ials

-0.79

merce

-0.71

 vacc

-0.71

 Deity

-0.68

ventures

-0.66

former

-0.65

ios

-0.64

 hust

-0.63

 apiece

-0.63

awaru

-0.63

POSITIVE LOGITS

 Expression

0.68

 OPEC

0.65

 Triangle

0.64

 Kepler

0.63

 Submission

0.62

 entitlement

0.62

olution

0.62

 Door

0.62

 mustard

0.61

 impunity

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.