INDEX

Explanations

references to configuration and setup instructions in software contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

BufferException

-0.68

HasAnnotation

-0.67

Демографія

-0.65

RTEX

-0.60

 contextLoads

-0.59

 }}$}

-0.57

WebServlet

-0.56

onAttach

-0.56

 NSCoder

-0.53

^(@)

-0.52

POSITIVE LOGITS

 yourself

0.70

 your

0.61

 astu

0.59

 propOrder

0.56

ροι

0.56

 ComVisible

0.56

 Yourself

0.53

 wisely

0.53

وی

0.52

picos

0.51

Activations Density 0.818%

references to configuration and setup instructions in software contexts

No Comments

No Known Activations