INDEX

Explanations

terms related to classifications and descriptions of mental health disorders

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

classification codes and symbols

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 OMITBAD

-0.47

 ComVisible

-0.46

 Савезне

-0.44

 صوتيه

-0.43

Dữ

-0.42

原始内容存档于

-0.42

ImageContext

-0.42

Наводи

-0.42

 NUKAT

-0.41

principalColumn

-0.40

POSITIVE LOGITS

 ujednoznacz

0.59

rawDesc

0.59

 labels

0.45

писок

0.44

 propOrder

0.43

 indisponible

0.41

 label

0.40

 amma

0.39

label

0.39

EndInit

0.36

Activations Density 0.001%

terms related to classifications and descriptions of mental health disorders

classification codes and symbols

No Comments

No Known Activations