INDEX

Explanations

technical terms and parameters related to graphical interfaces and controls

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

Code related to height and width

np_acts-logits-general · gemini-2.0-flash

dimensions and screen sizes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

cue

-0.43

des

-0.42

yy

-0.42

-0.41

SequentialGroup

-0.41

cup

-0.41

TestBed

-0.41

vu

-0.40

tu

-0.40

POSITIVE LOGITS

 greateſt

0.92

 myſelf

0.90

 himſelf

0.88

 itſelf

0.84

 Theſe

0.82

 fevere

0.81

 themſelves

0.79

IonicModule

0.78

 againſt

0.76

 leſs

0.76

Activations Density 0.559%

technical terms and parameters related to graphical interfaces and controls

Code related to height and width

dimensions and screen sizes

No Comments

No Known Activations