INDEX

Explanations

formatted comments or documentation in source code

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

 Мексичка

-0.63

 comuniques

-0.45

endphp

-0.45

 hroz

-0.42

+#+#

-0.41

oser

-0.41

paramref

-0.41

 دیکھیے

-0.40

__;

-0.39

 inapplicable

-0.39

POSITIVE LOGITS

SharedCtor

0.42

GTCX

0.40

Register

0.38

AntiForgeryToken

0.37

ibase

0.36

 Register

0.36

囗

0.36

laught

0.35

 register

0.35

posedge

0.35

Activations Density 0.003%

formatted comments or documentation in source code

<start_of_turn>user

No Comments

No Known Activations

formatted comments or documentation in source code

<start_of_turn>user

No Comments

No Known Activations