INDEX

Explanations

elements related to programming and networking terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.50

исленность

-0.48

GLC

-0.47

 Finance

-0.43

 Communication

-0.42

 määrä

-0.42

MethodManager

-0.42

 simpl

-0.41

‌آم

-0.41

のですね

-0.41

POSITIVE LOGITS

adaptiveStyles

0.52

AndEndTag

0.52

 disponibilités

0.49

 surla

0.47

 utafitiHapana

0.45

 semacam

0.44

 serupa

0.44

Hauptartikel

0.43

 varargin

0.43

cessite

0.43

Activations Density 1.909%

elements related to programming and networking terminology

No Comments

No Known Activations