INDEX

Explanations

phrases related to processes and actions in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 CreateTagHelper

-0.48

 genoeg

-0.47

伯

-0.47

jzen

-0.46

ELINES

-0.45

genommen

-0.45

ifikationer

-0.45

ise

-0.44

 richiesta

-0.43

isement

-0.43

POSITIVE LOGITS

 estekak

0.97

 then

0.83

then

0.70

CppCodeGen

0.68

 الحره

0.68

Then

0.67

 THEN

0.67

 AttributeSet

0.66

aarrggbb

0.63

DockStyle

0.62

Activations Density 0.389%

phrases related to processes and actions in programming or technical contexts

No Comments

No Known Activations