INDEX

Explanations

references to data processing commands and DataFrame manipulations in programming

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

pandas DataFrames (often shortened to "df")

np_acts-logits-general · gemini-2.0-flash

pandas DataFrame operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCompany

-0.30

throw

-0.30

di

-0.30

ReusableCell

-0.29

ListItemIcon

-0.29

bio

-0.29

paj

-0.28

 tele

-0.28

 stri

-0.28

 patern

-0.28

POSITIVE LOGITS

addContainerGap

0.59

oredCriteria

0.54

 miniaturka

0.53

SharedCtor

0.52

஦

0.50

<unused43>

0.50

<unused28>

0.49

<pad>

0.49

OGND

0.49

<unused23>

0.49

Activations Density 0.041%

references to data processing commands and DataFrame manipulations in programming

pandas DataFrames (often shortened to "df")

pandas DataFrame operations

No Comments

No Known Activations