INDEX

Explanations

intensifiers and degree modifiers that express strong emotion or commitment

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

following intensifiers

np_acts-logits-general · gemini-2.0-flash

adverbs and adjectives

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

cresc

-0.58

jíma

-0.49

mela

-0.49

wholesome

-0.48

 comprises

-0.48

inguém

-0.48

 contains

-0.47

IsNotNull

-0.47

nehå

-0.46

 lies

-0.46

POSITIVE LOGITS

UnsafeEnabled

0.84

uxxxx

0.82

EndProject

0.82

DockStyle

0.81

 aware

0.79

 AssemblyCulture

0.78

 nahilalakip

0.78

mybatisplus

0.78

 HasFactory

0.77

setVerticalGroup

0.76

Activations Density 0.249%

intensifiers and degree modifiers that express strong emotion or commitment

following intensifiers

adverbs and adjectives

No Comments

No Known Activations