INDEX

Explanations

phrases that involve conditions or circumstances under which events occur

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Bioaccumulative

-0.64

 propOrder

-0.53

'{@

-0.53

րջ

-0.53

iNdEx

-0.52

ỡng

-0.52

hljs

-0.49

 Clé

-0.49

 hikariConfig

-0.49

/**

-0.49

POSITIVE LOGITS

 comes

0.86

 doubt

0.70

enumi

0.66

 gäller

0.66

 gjelder

0.63

 pertains

0.62

 boil

0.60

 concerns

0.59

Dealing

0.58

 boils

0.57

Activations Density 0.180%

phrases that involve conditions or circumstances under which events occur

No Comments

No Known Activations