INDEX

Explanations

terms and expressions related to data indexing and manipulation in programming contexts

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

dataframe index assignment

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 <<<<<<<<<<<<<<

-0.65

awtextra

-0.60

///</

-0.57

\{\\

-0.56

ValueStyle

-0.54

 للمعارف

-0.52

 nonUne

-0.52

TagHelper

-0.52

__(/*!

-0.51

runApp

-0.51

POSITIVE LOGITS

 vectorielle

0.35

uche

0.35

 giro

0.34

 fourrure

0.34

Biographical

0.34

 Biographical

0.33

érias

0.33

 fort

0.33

edal

0.33

 Existe

0.32

Activations Density 0.005%

terms and expressions related to data indexing and manipulation in programming contexts

dataframe index assignment

No Comments

No Known Activations