INDEX

Explanations

high values indicating important or significant coding constructs or directives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

”

-0.56

νη

-0.56

Salta

-0.54

-0.52

↵

-0.51

“

-0.51

[]:

-0.51

-0.50

-0.49

 صوتيه

-0.49

POSITIVE LOGITS

ItemBackground

0.92

 <>",

0.86

astéroïdes

0.83

 disambiguazione

0.81

ьаж

0.77

AsUp

0.75

Diwedd

0.74

 Bourgoin

0.73

:✨

0.71

ReusableCell

0.70

Activations Density 0.064%

high values indicating important or significant coding constructs or directives

No Comments

No Known Activations