INDEX

Explanations

special formatting markers or control characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

learner

-0.60

aarrggbb

-0.58

Història

-0.58

 Dutta

-0.58

FYI

-0.58

Carriera

-0.57

 Tenggara

-0.57

 Leech

-0.56

XmlIgnore

-0.55

Примечания

-0.55

POSITIVE LOGITS

0.83

0.82

×

0.79

bonucle

0.79

0.78

0.76

Activations Density 0.019%

special formatting markers or control characters

No Comments

No Known Activations