INDEX

Explanations

references to location and burial contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 doInBackground

-0.74

存于互联网档案馆

-0.69

 webdriver

-0.66

WindowConstants

-0.66

ksikon

-0.66

ukone

-0.65

Revenir

-0.64

PreferredItem

-0.63

 everything

-0.63

BindingResult

-0.62

POSITIVE LOGITS

➟

0.64

 mijne

0.61

Solución

0.54

 jasa

0.53

 parlour

0.53

 "..\..\

0.53

MessageOf

0.52

Tembelea

0.52

Indented

0.52

endete

0.51

Activations Density 0.048%

references to location and burial contexts

No Comments

No Known Activations