INDEX

Explanations

various forms of punctuation marks, particularly brackets and periods

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

```end of sentence or clause```

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

 rég

-0.38

Ash

-0.30

抚

-0.29

ทาง

-0.29

ֵי

-0.29

dis

-0.29

 ancient

-0.28

รอบ

-0.28

းက

-0.27

 dark

-0.27

POSITIVE LOGITS

ChildScrollView

0.85

 snippetHide

0.75

<unused52>

0.73

<unused8>

0.73

<unused14>

0.73

<unused43>

0.73

<unused74>

0.73

<unused41>

0.73

<unused16>

0.73

<unused28>

0.73

Activations Density 0.005%

various forms of punctuation marks, particularly brackets and periods

```end of sentence or clause```

No Comments

No Known Activations