INDEX

Explanations

code segments or structure related to graphical user interface components in programming

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

Follows specific tokens like "use", "born", ")$", or "neg"

np_acts-logits-general · gemini-2.0-flash

use with string or this

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Rüyada

-0.84

IntoConstraints

-0.63

yelitis

-0.63

 SDLK

-0.63

 OGSÅ

-0.62

ItemBackground

-0.60

ksikon

-0.60

Portale

-0.59

AsUp

-0.58

writeField

-0.58

POSITIVE LOGITS

this

0.82

tslib

0.54

 francès

0.53

SizeF

0.52

resources

0.51

org

0.51

font

0.50

XmlType

0.49

ths

0.48

ιο

0.48

Activations Density 0.004%

code segments or structure related to graphical user interface components in programming

Follows specific tokens like "use", "born", ")$", or "neg"

use with string or this

No Comments

No Known Activations