INDEX

Explanations

various forms of the word "plot" and related terms in graphical contexts

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

plot or plotter

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Naissance

-0.66

Imm

-0.61

 defStyleAttr

-0.60

 Sabrina

-0.59

 Personalized

-0.59

 Rina

-0.58

 Superhost

-0.58

 newUser

-0.58

"""

-0.57

ervices

-0.56

POSITIVE LOGITS

plot

1.15

 plot

1.12

Plot

1.01

 Plot

1.00

 PLOT

0.97

 plots

0.85

 Plots

0.84

PLOT

0.81

Plots

0.79

 plotter

0.79

Activations Density 0.014%

various forms of the word "plot" and related terms in graphical contexts

plot or plotter

No Comments

No Known Activations