INDEX

Explanations

mathematical expressions and parameters related to rotations and transformations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ModelExpression

-0.83

 <=",

-0.65

expandindo

-0.60

 ditem

-0.55

énario

-0.52

ConstraintMaker

-0.52

 Castle

-0.52

 uLocal

-0.51

vik

-0.51

Castle

-0.50

POSITIVE LOGITS

氪

0.55

RuleContext

0.54

holes

0.52

Holes

0.51

 holes

0.50

hole

0.49

Tembelea

0.48

 Diner

0.48

 Holes

0.47

otoro

0.46

Activations Density 0.789%

mathematical expressions and parameters related to rotations and transformations

No Comments

No Known Activations