INDEX

Explanations

terms related to experimental procedures or scientific methodologies

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

start of turn user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 argint

-0.47

الحياه

-0.46

makeText

-0.44

 olvido

-0.43

HasForeignKey

-0.42

 détruire

-0.40

OGND

-0.39

 AssemblyVersion

-0.39

mbalikan

-0.38

 चुनें

-0.37

POSITIVE LOGITS

httphttps

0.83

</blockquote>

0.57

expandindo

0.55

Datuak

0.48

AddTagHelper

0.47

 Tapatalk

0.46

 IndexPath

0.46

 utafitiHapana

0.46

 informée

0.46

 ProtoMessage

0.45

Activations Density 0.000%

terms related to experimental procedures or scientific methodologies

start of turn user

No Comments

No Known Activations