INDEX

Explanations

language identifiers related to documentation and metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

__":

-0.96

RenderAtEndOf

-0.94

__":

-0.91

queryInterface

-0.87

%"),

-0.84

IVEREF

-0.84

Hochspringen

-0.83

"]);

-0.83

()]);

-0.81

WithIOException

-0.81

POSITIVE LOGITS

 English

0.46

Ru

0.45

english

0.43

Ru

0.42

 latine

0.42

prüche

0.42

ru

0.42

Sh

0.42

 Meksiku

0.41

fr

0.41

Activations Density 0.140%

language identifiers related to documentation and metadata

No Comments

No Known Activations