INDEX

Explanations

phrases indicating joint actions or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 تانيه

-1.01

 ویکی‌پدیا

-0.79

ArgsConstructor

-0.72

ChildScrollView

-0.71

 الدولى

-0.68

ocratic

-0.66

HomeAsUpEnabled

-0.66

Geplaatst

-0.65

ocracy

-0.65

ificato

-0.65

POSITIVE LOGITS

and

0.64

or

0.53

 betweenstory

0.48

 writes

0.48

 motor

0.47

GMENT

0.46

 uwagę

0.46

0.43

 metal

0.42

Activations Density 0.697%

phrases indicating joint actions or situations

No Comments

No Known Activations