INDEX

Explanations

references to holes or openings in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

קישורים

-0.87

GraphicsUnit

-0.86

">//

-0.84

aarrggbb

-0.83

anyahu

-0.78

neapolis

-0.77

 otomatig

-0.73

Portail

-0.71

 genitori

-0.70

хьтан

-0.70

POSITIVE LOGITS

 hole

1.41

 holes

1.36

hole

1.35

 Hole

1.34

 Holes

1.31

 HOLE

1.30

Hole

1.30

Holes

1.25

HOLE

1.20

holes

1.11

Activations Density 0.175%

references to holes or openings in various contexts

No Comments

No Known Activations