INDEX

Explanations

references to characters and their relationships

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

 mukana

-0.51

<_>

-0.47

چی

-0.45

 sleeves

-0.45

 aikana

-0.44

værende

-0.44

 elbows

-0.44

 faptul

-0.43

 sveta

-0.43

yor

-0.43

POSITIVE LOGITS

 propOrder

0.87

RegistryLite

0.83

ThroughAttribute

0.80

cshtml

0.75

DeleteBehavior

0.72

resave

0.72

 gynhyrchwyd

0.72

ImageContext

0.70

BindingResult

0.70

 GenerationType

0.68

Activations Density 0.368%

references to characters and their relationships

No Comments

No Known Activations