INDEX

Explanations

statistical terms and measurements related to mean values, averages, and deviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

MigrationBuilder

-0.66

 lenker

-0.63

ViewFeatures

-0.57

sides

-0.56

 OnEnable

-0.55

phorus

-0.55

Bioaccumulative

-0.54

Enlaces

-0.53

ContentAsync

-0.53

awtextra

-0.53

POSITIVE LOGITS

 litté

0.70

urement

0.68

lessness

0.62

 reversion

0.60

spirited

0.60

fulness

0.60

 spirited

0.60

tioned

0.58

 endwhile

0.57

cillor

0.57

Activations Density 0.118%

statistical terms and measurements related to mean values, averages, and deviations

No Comments

No Known Activations