INDEX

Explanations

references to specific authors and their works or opinions on political topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RTEX

-0.82

出版年

-0.78

PerformLayout

-0.77

SharedCtor

-0.75

 समीक्षाओं

-0.75

 AssemblyCulture

-0.73

 виправивши

-0.71

DispatchToProps

-0.71

 HasFactory

-0.70

 Réponses

-0.70

POSITIVE LOGITS

 Slate

0.55

 essay

0.55

著

0.48

Slate

0.47

 argues

0.47

NPR

0.47

 Netflix

0.45

substack

0.45

 essays

0.44

âne

0.43

Activations Density 0.374%

references to specific authors and their works or opinions on political topics

No Comments

No Known Activations