INDEX

Explanations

references to specific brands or products related to vehicles and media

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

Text after quotation marks/punctuation

np_acts-logits-general · gemini-2.0-flash

references followed by metadata

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

TextWatcher

-0.51

 JpaRepository

-0.51

 bParam

-0.50

Iné

-0.50

 AÑOS

-0.50

})->

-0.48

addPreferredGap

-0.47

 PropertyChanged

-0.46

stdarg

-0.45

ัจ

-0.45

POSITIVE LOGITS

 betweenstory

0.81

【

0.63

protoimpl

0.61

IndentedString

0.61

《

0.60

0.59

El

0.59

关于

0.59

 Review

0.58

Review

0.58

Activations Density 0.125%

references to specific brands or products related to vehicles and media

Text after quotation marks/punctuation

references followed by metadata

No Comments

No Known Activations