INDEX

Explanations

locations and movements within physical spaces

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

is

-0.60

-0.49

 consider

-0.48

for

-0.48

you

-0.47

-0.46

has

-0.46

-0.45

-0.44

 considered

-0.43

POSITIVE LOGITS

AnchorStyles

1.01

 виправивши

0.97

 houſe

0.92

 المعيارى

0.91

 للمعارف

0.91

HostException

0.90

hematical

0.89

ConstraintMaker

0.88

ScopeManager

0.87

 downstairs

0.86

Activations Density 0.217%

locations and movements within physical spaces

No Comments

No Known Activations