INDEX

Explanations

references to scientific or medical data points

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

Code, comments, and file paths

np_acts-logits-general · gemini-2.0-flash

Complimentary Samples

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

RequestBuilder

-0.46

roslav

-0.45

 review

-0.45

ago

-0.44

izo

-0.44

 Note

-0.44

rank

-0.43

 note

-0.42

 Single

-0.42

 ennemi

-0.42

POSITIVE LOGITS

клопе

1.04

 gynhyrchwyd

0.97

AddTagHelper

0.87

WaitGroup

0.78

 typelib

0.77

 חיצוניים

0.74

WebVitals

0.74

 '\\;'

0.73

脚注の使い方

0.72

Xna

0.71

Activations Density 0.119%

references to scientific or medical data points

Code, comments, and file paths

Complimentary Samples

No Comments

No Known Activations