INDEX

Explanations

references to interpersonal or relational dynamics, often highlighting tension or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

IntoConstraints

-1.01

AsUp

-0.82

DockStyle

-0.77

 CURIAM

-0.71

PerformLayout

-0.66

twimg

-0.66

OGND

-0.65

 disambiguazione

-0.65

adaptiveStyles

-0.64

principalColumn

-0.64

POSITIVE LOGITS

 narrator

0.69

 literary

0.66

 foreshadow

0.64

 readers

0.62

 author

0.62

 reader

0.62

作者

0.59

 simile

0.58

Literary

0.57

 Author

0.54

Activations Density 0.148%

references to interpersonal or relational dynamics, often highlighting tension or conflict

No Comments

No Known Activations