INDEX

Explanations

phrases related to research findings and their implications

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

addCriterion

-0.76

ValueStyle

-0.76

verwijspagina

-0.75

 defaultstate

-0.74

 disambiguazione

-0.73

Хьажоргаш

-0.72

ViewFeatures

-0.71

UnsafeEnabled

-0.70

IntoConstraints

-0.68

PreferredItem

-0.66

POSITIVE LOGITS

 caution

0.69

 suggesting

0.66

 further

0.66

 suggests

0.65

 suggest

0.65

 underscores

0.65

唆

0.62

 highlight

0.60

 underscore

0.58

 suggested

0.58

Activations Density 2.076%

phrases related to research findings and their implications

No Comments

No Known Activations