INDEX

Explanations

numbers and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

SharedCtor

-0.72

Попис

-0.49

Lähteet

-0.49

 muualla

-0.49

Eksterne

-0.49

assertThat

-0.48

didSet

-0.47

har

-0.46

mybatisplus

-0.46

Ay

-0.46

POSITIVE LOGITS

PointSize

0.55

Tikang

0.53

HostException

0.53

 Wikiquote

0.52

supplement

0.51

 oublié

0.51

 HasFactory

0.51

JspWriter

0.51

 referenties

0.51

eqn

0.50

Activations Density 0.024%

numbers and their relationships

No Comments

No Known Activations