INDEX

Explanations

references to technical or scientific notation and mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 itſelf

-1.03

 Majefty

-0.82

 themſelves

-0.78

 pleaſure

-0.78

 fhort

-0.75

 Anſ

-0.73

 myſelf

-0.73

 himſelf

-0.73

 fubject

-0.73

 Comédie

-0.72

POSITIVE LOGITS

=""/>

0.60

 mergeFrom

0.53

SharedDtor

0.52

 дописавши

0.52

 ***!

0.51

erialization

0.50

matchCondition

0.50

providedIn

0.49

]--;

0.47

englanniksi

0.47

Activations Density 2.137%

references to technical or scientific notation and mathematical expressions

No Comments

No Known Activations