INDEX

Explanations

quantifiers and articles in German text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Exactos

-0.59

více

-0.58

 ſtand

-0.54

liau

-0.54

 Untersch

-0.54

 invokingState

-0.54

таратура

-0.53

formKey

-0.53

 getopt

-0.52

собенно

-0.52

POSITIVE LOGITS

 eine

1.94

 einen

1.80

 einer

1.65

eine

1.53

 einem

1.50

Eine

1.46

 isang

1.42

 một

1.40

 sebuah

1.38

 Eine

1.35

Activations Density 0.038%

quantifiers and articles in German text

No Comments

No Known Activations