INDEX

Explanations

references to the concept of judgment or evaluation

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

Personensuche

-0.76

 kasarigan

-0.68

homonymie

-0.62

 cherchés

-0.61

expandindo

-0.61

-0.60

SourceChecksum

-0.57

 препратки

-0.56

 utafitiHapana

-0.56

ScopeManager

-0.55

POSITIVE LOGITS

lot

0.73

](#

0.54

 aéreas

0.53

 certain

0.52

isier

0.48

 trace

0.48

 edelstahl

0.46

 altro

0.44

ariConfig

0.43

rous

0.43

Activations Density 0.141%

references to the concept of judgment or evaluation

No Comments

No Known Activations