INDEX

Explanations

references to statistical estimates or metrics related to studies

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

Numerical data, statistics, and calculations

np_acts-logits-general · gemini-2.0-flash

statistical figures and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 transfieras

-0.55

gonic

-0.55

fromCharCode

-0.55

OGND

-0.54

]='\

-0.54

 ResponseEntity

-0.50

 BoxDecoration

-0.48

Xna

-0.48

 Durée

-0.48

antaine

-0.47

POSITIVE LOGITS

 calculation

1.05

 accurate

1.01

 calculations

1.00

 accuracy

0.97

Accurate

0.93

 computation

0.92

 inaccurate

0.91

Calculation

0.90

accurate

0.89

 calculating

0.87

Activations Density 0.814%

references to statistical estimates or metrics related to studies

Numerical data, statistics, and calculations

statistical figures and calculations

No Comments

No Known Activations