INDEX

Explanations

terms related to optimization processes

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

optimizing efficiency and results

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

цезда

-0.58

 radioButton

-0.53

 Scatter

-0.50

 Pans

-0.48

posedge

-0.47

 CURIAM

-0.45

Scatter

-0.43

竇

-0.43

acterial

-0.42

gatsby

-0.42

POSITIVE LOGITS

optimize

2.20

 optimize

2.11

 Optimize

1.86

Optimize

1.82

 optimise

1.75

 optimizing

1.70

optim

1.57

 optim

1.55

Optim

1.47

 Optim

1.46

Activations Density 0.003%

terms related to optimization processes

optimizing efficiency and results

No Comments

No Known Activations