INDEX

Explanations

technical terms related to model evaluation and session management in machine learning

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

mathematical trace `Tr`

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

ⓧ

-0.65

 Chapin

-0.45

shmi

-0.44

 islas

-0.44

balanceOf

-0.44

 marrying

-0.44

 missão

-0.44

 Burke

-0.42

 esperança

-0.42

 vantaggio

-0.41

POSITIVE LOGITS

GOTREF

0.51

 OMITBAD

0.50

sess

0.49

MockMvc

0.48

 sess

0.47

posedge

0.45

OCCURRED

0.45

+#+#

0.44

MigrationBuilder

0.44

 Wicidata

0.44

Activations Density 0.008%

technical terms related to model evaluation and session management in machine learning

mathematical trace `Tr`

No Comments

No Known Activations