INDEX

Explanations

phrases related to ongoing discussions or proposals in various contexts

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

past actions and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

MemoryWarning

-0.44

 symptoms

-0.38

 auroit

-0.37

 conso

-0.37

 ModelExpression

-0.36

IntoConstraints

-0.36

 physical

-0.35

 LIRE

-0.35

PrintWriter

-0.34

 juſt

-0.33

POSITIVE LOGITS

OGND

0.57

AnchorTagHelper

0.54

 informée

0.52

iligung

0.50

FormTagHelper

0.46

GTCX

0.45

 ochi

0.44

 Assignee

0.44

 ExecuteAsync

0.43

RefNanny

0.43

Activations Density 0.067%

phrases related to ongoing discussions or proposals in various contexts

past actions and findings

No Comments

No Known Activations