INDEX

Explanations

different types or instances of empty objects or structures in the document

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

academic paper citations

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

autogui

-0.40

-0.38

ald

-0.38

Gall

-0.36

adc

-0.35

깐

-0.35

്ട

-0.35

↵↵↵

-0.35

rec

-0.35

POSITIVE LOGITS

{},

1.36

{},

1.30

{})

1.23

{},

1.05

 يتيمه

0.98

{};

0.95

{};

0.94

({},

0.94

{})

0.87

 {}),

0.85

Activations Density 0.023%

different types or instances of empty objects or structures in the document

academic paper citations

No Comments

No Known Activations