INDEX

Explanations

references to system components or functions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:✨

-0.82

thâu

-0.79

SharedDtor

-0.79

fjspx

-0.72

itemBuilder

-0.70

hoeddwyd

-0.69

SourceChecksum

-0.69

NameInMap

-0.67

лтемелер

-0.66

buttonBar

-0.66

POSITIVE LOGITS

 System

0.76

System

0.67

stood

0.57

ValueStyle

0.55

tagHelperRunner

0.54

SYSTEM

0.52

ėd

0.50

eqn

0.49

 SYSTEM

0.49

 Newtonsoft

0.49

Activations Density 0.003%

references to system components or functions in code

No Comments

No Known Activations