INDEX

Explanations

specific configuration settings or parameters

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 @ 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

)))),

-0.44

 виправивши

-0.42

 Extragalactic

-0.42

 Corbu

-0.41

uilla

-0.38

watching

-0.38

 insuffisamment

-0.37

']->

-0.37

จบ

-0.37

 IEnumerator

-0.37

POSITIVE LOGITS

 mView

0.54

 next

0.53

AnimationsModule

0.50

StoryboardSegue

0.48

Next

0.48

next

0.47

 Next

0.46

CppMethod

0.46

+#+#

0.45

 NEXT

0.42

Activations Density 0.000%

specific configuration settings or parameters

<start_of_turn>user

No Comments

No Known Activations