INDEX

Explanations

references to academic standards and documentation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 فريبيس

-0.71

Personendaten

-0.70

 pinulongan

-0.69

AddHtmlAttribute

-0.67

 <=",

-0.66

InstrumentedTest

-0.65

DockStyle

-0.64

MemoryWarning

-0.64

IntoConstraints

-0.64

ValueStyle

-0.63

POSITIVE LOGITS

hematical

0.51

 kinematic

0.50

underwater

0.49

Hinter

0.48

PARTIC

0.48

\|\

0.48

ryd

0.47

ayos

0.46

yaratan

0.45

rinth

0.45

Activations Density 0.083%

references to academic standards and documentation processes

No Comments

No Known Activations