INDEX

Explanations

references to a specific term or acronym related to deep learning or machine learning

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

dL or <start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.54

 <>",

-0.52

 Comprometido

-0.51

Personensuche

-0.48

 invokingState

-0.47

Colour

-0.44

 colour

-0.42

rungsseite

-0.42

TagHelper

-0.42

homonymie

-0.42

POSITIVE LOGITS

DropTable

3.08

Према

1.33

Portale

0.58

ISupport

0.50

mergeFrom

0.46

XDECREF

0.46

DECREF

0.43

 للاسماء

0.43

BeginInit

0.43

 Drop

0.42

Activations Density 0.000%

references to a specific term or acronym related to deep learning or machine learning

dL or <start_of_turn> user

No Comments

No Known Activations