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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Wi

-0.78

vez

-0.77

IQ

-0.75

actionDate

-0.74

Merit

-0.73

Marx

-0.72

psc

-0.71

eston

-0.70

owa

-0.70

Lenin

-0.69

POSITIVE LOGITS

 prosecuting

0.72

 whore

0.69

 Author

0.64

 violet

0.63

 masculine

0.63

 separated

0.61

aving

0.61

Ã´

0.61

olves

0.60

 torment

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.