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

rium

-0.83

Viz

-0.73

 unprotected

-0.73

Fur

-0.65

 Dahl

-0.64

 cabinets

-0.63

 seism

-0.62

 cavern

-0.62

 vault

-0.60

Ig

-0.60

POSITIVE LOGITS

Benef

0.77

advertisement

0.75

Closure

0.75

OUR

0.74

THIS

0.74

Translation

0.73

OVER

0.73

operator

0.72

ERE

0.72

GL

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.