INDEX

Explanations

terms related to layers, compounds, or entities involved in biological or chemical processes

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

followed by forms of "serve" or "act"

np_acts-logits-general · gemini-2.0-flash

acts, serves, promotes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ngdoc

-0.58

enumi

-0.55

MLLoader

-0.53

,‎

-0.52

mogorov

-0.50

Composable

-0.49

 Wikispecies

-0.49

/\.

-0.49

ultuous

-0.48

 envol

-0.47

POSITIVE LOGITS

 serve

2.17

 serves

2.09

act

1.96

 acts

1.89

 Serve

1.86

 acted

1.86

 serving

1.83

serve

1.80

 served

1.78

 Serves

1.77

Activations Density 0.779%

terms related to layers, compounds, or entities involved in biological or chemical processes

followed by forms of "serve" or "act"

acts, serves, promotes

No Comments

No Known Activations