INDEX

Explanations

phrases indicating gratitude or humility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

NOPQRST

-0.94

EndInit

-0.78

CPtr

-0.74

StoryboardSegue

-0.74

:✨

-0.73

RTGC

-0.73

MemoryWarning

-0.73

ⓧ

-0.69

TypedDataSet

-0.69

 Walkover

-0.68

POSITIVE LOGITS

 self

0.55

 selfless

0.53

self

0.53

 Self

0.51

Self

0.47

 insisted

0.47

 SELF

0.46

謙

0.43

 insiste

0.42

 volunteered

0.42

Activations Density 0.118%

phrases indicating gratitude or humility

No Comments

No Known Activations