INDEX

Explanations

numerical values and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

*/].

-0.51

 }^{(

-0.50

<_>

-0.50

rboles

-0.49

PrototypeOf

-0.48

memoized

-0.48

 Ceramby

-0.47

 OMITBAD

-0.47

ēja

-0.46

<!--[

-0.46

POSITIVE LOGITS

SequentialGroup

0.66

MemoryWarning

0.64

 JpaRepository

0.61

ViewStyle

0.59

InputBorder

0.59

laubnis

0.59

 Roskov

0.58

hidupan

0.56

 Chwiliwch

0.54

 cerebellum

0.53

Activations Density 0.325%

numerical values and measurements

No Comments

No Known Activations