INDEX

Explanations

references to inner and outer components or concepts in various contexts

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

the word "inner" appearing in various technical and non-technical contexts.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 transfieras

-0.49

tagHelperRunner

-0.49

 pinulongan

-0.48

SBATCH

-0.48

bibitem

-0.42

addContainerGap

-0.40

 Drapeau

-0.39

sendRedirect

-0.37

/*++

-0.36

 препратки

-0.36

POSITIVE LOGITS

 Inner

0.97

 inner

0.95

Inner

0.92

 INNER

0.89

 Outer

0.86

inner

0.84

Outer

0.80

 innermost

0.78

INNER

0.77

outer

0.73

Activations Density 0.085%

references to inner and outer components or concepts in various contexts

the word "inner" appearing in various technical and non-technical contexts.

No Comments

No Known Activations