INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ļéĨĴ

-0.75

 Marathon

-0.70

EAR

-0.65

 Mandatory

-0.64

 Lifetime

-0.64

HIP

-0.63

WW

-0.63

Yel

-0.60

 GDDR

-0.60

 Pioneer

-0.59

POSITIVE LOGITS

 checkpoints

0.77

airs

0.76

eret

0.76

 stalls

0.74

ubb

0.73

ourses

0.69

Ds

0.68

resses

0.66

ock

0.65

Ã£

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.