INDEX

Explanations

phrases related to mechanisms and processes in scientific contexts, particularly those involving direct effects and interactions

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

Expressing means or agency

np_acts-logits-general · gemini-2.0-flash

describing a method

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

]")]

-0.78

webElementXpaths

-0.69

Tikang

-0.67

("}");

-0.60

AddTagHelper

-0.60

--;

-0.58

EnableWeb

-0.58

everything

-0.58

Initializable

-0.58

 صوتيه

-0.57

POSITIVE LOGITS

 behulp

1.01

 means

1.00

 biais

0.98

 помощью

0.97

 pamamagitan

0.95

 through

0.95

Through

0.89

via

0.88

 Through

0.87

through

0.86

Activations Density 0.711%

phrases related to mechanisms and processes in scientific contexts, particularly those involving direct effects and interactions

Expressing means or agency

describing a method

No Comments

No Known Activations