INDEX

Explanations

mentions of specific TV shows and movie adaptations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

✨:

-0.48

rašymas

-0.47

%"),

-0.43

}}],

-0.42

//});

-0.42

 geleden

-0.41

lês

-0.41

ärke

-0.41

Skocz

-0.40

irii

-0.40

POSITIVE LOGITS

 Jurassic

0.71

 Transformers

0.70

 Harry

0.70

The

0.69

 Titanic

0.66

 Seinfeld

0.65

 Avengers

0.65

tagHelperRunner

0.64

 Pokémon

0.64

 Shrek

0.64

Activations Density 0.456%

mentions of specific TV shows and movie adaptations

No Comments

No Known Activations