INDEX

Explanations

technical terms and processes related to programming and software configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 photolibrary

-0.72

,’’

-0.72

catchError

-0.69

),”

-0.67

>*/

-0.66

,’

-0.65

Sucesor

-0.64

TargetException

-0.64

.’’

-0.62

>");

-0.62

POSITIVE LOGITS

 comportement

0.81

 contextes

0.71

 runtime

0.69

 behaviour

0.69

 behaviours

0.68

 optionally

0.68

behaviour

0.67

{@

0.67

 arbitrary

0.65

 TODO

0.65

Activations Density 3.594%

technical terms and processes related to programming and software configuration

No Comments

No Known Activations