INDEX

Explanations

terms related to data analysis and parsing processes

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

Parsing and interpretation

np_acts-logits-general · gemini-2.0-flash

parsing and interpretation of data

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

AsUp

-0.68

+#+#

-0.67

 moelle

-0.67

帖最后由

-0.66

 AssemblyCulture

-0.66

orianCalendar

-0.63

لكتر

-0.62

defineProperty

-0.61

 بيها

-0.59

roveň

-0.58

POSITIVE LOGITS

 Parse

0.84

 interpre

0.83

 interpretar

0.80

 解析

0.78

 Parsing

0.78

 interpret

0.77

 parsing

0.77

 parse

0.75

parse

0.75

interpre

0.74

Activations Density 0.355%

terms related to data analysis and parsing processes

Parsing and interpretation

parsing and interpretation of data

No Comments

No Known Activations