INDEX

Explanations

code-related structures and constructs

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

nimmt

-0.42

рока

-0.41

if

-0.40

 разо

-0.39

ung

-0.39

capa

-0.38

wall

-0.38

 wall

-0.37

QUADS

-0.36

</em>

-0.36

POSITIVE LOGITS

expandindo

1.53

CppMethod

0.96

 للاسماء

0.86

 pinulongan

0.85

 Normdatei

0.83

ArgsConstructor

0.83

 Мексичка

0.82

StructEnd

0.81

Enllaços

0.79

 disambiguazione

0.78

Activations Density 0.161%

code-related structures and constructs

No Comments

No Known Activations