INDEX

Explanations

specific actions, processes, or conditions related to functionality and adjustments

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

 समीक्षाएं

-0.58

providedIn

-0.51

getActiveSheet

-0.50

المشاركات

-0.48

UpInside

-0.48

pyx

-0.47

.*")]

-0.46

UrlResolution

-0.46

arabe

-0.45

rinology

-0.44

POSITIVE LOGITS

 itself

0.85

 Itself

0.74

itself

0.73

 covers

0.60

covers

0.58

 zufolge

0.58

gives

0.57

 گوید

0.57

andaag

0.56

 gives

0.55

Activations Density 0.842%

specific actions, processes, or conditions related to functionality and adjustments

No Comments

No Known Activations