INDEX

Explanations

phrases and keywords related to organizational and operational policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 valentín

-0.62

MethodManager

-0.55

 feroit

-0.53

 avoient

-0.52

colgante

-0.52

 increí

-0.50

 auroit

-0.49

đầm

-0.49

ilustración

-0.48

 semelh

-0.48

POSITIVE LOGITS

TypedDataSet

0.38

 Inverse

0.37

 Eval

0.37

Dil

0.36

Ron

0.35

DIL

0.35

 виправивши

0.35

 بالس

0.35

ø

0.34

Til

0.34

Activations Density 1.406%

phrases and keywords related to organizational and operational policies

No Comments

No Known Activations