INDEX

Explanations

coding terms and function declarations

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

after "open" and capitalized words

np_acts-logits-general · gemini-2.0-flash

open, negatively, skewed

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

ActionCreators

-0.73

isseurs

-0.66

 وتسجيلات

-0.65

jsxFileName

-0.64

DispatchToProps

-0.64

Zunanje

-0.63

flashdata

-0.63

ApiOperation

-0.62

hintText

-0.61

nextProps

-0.60

POSITIVE LOGITS

tagHelperRunner

0.46

 older

0.46

ORAGE

0.44

яд

0.44

Older

0.44

 Older

0.44

vaz

0.44

Smaller

0.43

tettu

0.43

WebControls

0.43

Activations Density 0.336%

coding terms and function declarations

after "open" and capitalized words

open, negatively, skewed

No Comments

No Known Activations