INDEX

Explanations

sequences of numbers or numerical data

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 @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Italij

-0.42

IntoConstraints

-0.40

 république

-0.39

 amanhã

-0.39

 kebenaran

-0.38

 dianteiro

-0.38

 prossima

-0.37

 borracha

-0.36

Besides

-0.35

Amical

-0.35

POSITIVE LOGITS

BufferException

0.59

extAlignment

0.48

PageRoute

0.48

 שוליים

0.47

Попис

0.46

interopRequire

0.45

SharedCtor

0.45

expandindo

0.45

CodedInputStream

0.44

 autorytatywna

0.43

Activations Density 0.004%

sequences of numbers or numerical data

<start_of_turn>user

No Comments

No Known Activations