INDEX

Explanations

negations or expressions of doubt

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

Follows "take" or "not"

np_acts-logits-general · gemini-2.0-flash

short duration or negation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

antMatchers

-0.60

 كومونز

-0.57

St

-0.53

таратура

-0.51

Vidite

-0.49

Svar

-0.48

}{*}{

-0.47

../

-0.47

riors

-0.46

onReady

-0.45

POSITIVE LOGITS

 quæ

0.66

GEBURTSDATUM

0.62

 jsPsych

0.60

ModelBuilder

0.60

CodedInputStream

0.60

 leſs

0.59

TagMode

0.59

utilisons

0.58

HideFlags

0.57

 doubtnut

0.56

Activations Density 0.216%

negations or expressions of doubt

Follows "take" or "not"

short duration or negation

No Comments

No Known Activations