INDEX

Explanations

HTML elements and classes associated with icons or graphical representations

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

Code or technical jargon

np_acts-logits-general · gemini-2.0-flash

mphonic sounds

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

colhead

-0.71

setVerticalGroup

-0.66

prüche

-0.64

expandindo

-0.64

 PublicKey

-0.63

EndContext

-0.61

IVEREF

-0.61

permitAll

-0.61

fromnode

-0.59

ukone

-0.59

POSITIVE LOGITS

vora

0.58

 plug

0.55

 alam

0.54

Pkg

0.52

ticons

0.50

información

0.50

 green

0.49

 glyphicon

0.49

 money

0.49

 downward

0.49

Activations Density 0.095%

HTML elements and classes associated with icons or graphical representations

Code or technical jargon

mphonic sounds

No Comments

No Known Activations