INDEX

Explanations

references to programming libraries and functions related to data manipulation and analysis

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

Python library imports (numpy, pandas, tensorflow)

np_acts-logits-general · gemini-2.0-flash

Python library abbreviations and calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 TextInputType

-0.74

HostException

-0.74

ParallelGroup

-0.72

 BoxFit

-0.70

transQ

-0.66

 betweenstory

-0.64

StoryboardSegue

-0.63

PostExecute

-0.62

waitKey

-0.61

ApiModelProperty

-0.61

POSITIVE LOGITS

0.77

 المعيارى

0.56

utils

0.55

 "..\..\

0.55

util

0.54

._

0.53

stdc

0.49

 import

0.49

ware

0.48

包

0.44

Activations Density 0.070%

references to programming libraries and functions related to data manipulation and analysis

Python library imports (numpy, pandas, tensorflow)

Python library abbreviations and calls

No Comments

No Known Activations