INDEX

Explanations

mathematical expressions and symbols

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

spelling bee

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

MigrationBuilder

-0.81

expandindo

-0.75

 estekak

-0.73

 MainAxisSize

-0.69

WebVitals

-0.68

ſammen

-0.68

 queſto

-0.67

niſſe

-0.66

<pad>

-0.66

iſchen

-0.66

POSITIVE LOGITS

↵↵

0.42

↵

0.33

<eos>

0.32

</em>

0.32

《

0.30

0.29

↵↵↵↵

0.28

</u>

0.28

imp

0.28

↵↵↵

0.28

Activations Density 0.001%

mathematical expressions and symbols

spelling bee

No Comments

No Known Activations