INDEX

Explanations

code-related placeholders or directives in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

-0.44

Buildable

-0.44

-0.43

-0.42

/*

-0.41

<eos>

-0.39

//

-0.39

POSITIVE LOGITS

Lähteet

2.14

rungsseite

2.09

 autorytatywna

1.98

Przypisy

1.91

Bronnen

1.88

Einzelnachweise

1.84

Referències

1.81

 kasarigan

1.77

 disambiguazione

1.73

Hochspringen

1.72

Activations Density 0.015%

code-related placeholders or directives in programming contexts

No Comments

No Known Activations