INDEX

Explanations

technical jargon and code-related terms from various programming languages and libraries

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

Characters such as punctuation and start of turn markers

np_acts-logits-general · gemini-2.0-flash

<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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

EndContext

-0.52

 виправивши

-0.48

InstrumentedTest

-0.47

tagHelperRunner

-0.45

BeginContext

-0.43

 кӀ

-0.40

 Dostupné

-0.35

hfill

-0.34

 ویکی‌پدیای

-0.34

-------------</

-0.32

POSITIVE LOGITS

рант

0.50

endcsname

0.48

 subsequently

0.48

antMatchers

0.47

Portale

0.47

sequently

0.46

 also

0.46

袂

0.46

ioren

0.46

 Legion

0.45

Activations Density 0.062%

technical jargon and code-related terms from various programming languages and libraries

Characters such as punctuation and start of turn markers

<start_of_turn>user

No Comments

No Known Activations