INDEX

Explanations

numeric values related to exam scores and their derived calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ỡng

-0.75

rrggbb

-0.70

 intStringLen

-0.67

 مرئيه

-0.67

AndEndTag

-0.67

CppCodeGen

-0.66

ymce

-0.66

RenderAtEndOf

-0.65

EndGlobalSection

-0.65

⟬

-0.65

POSITIVE LOGITS

 grades

0.43

 student

0.43

 grade

0.42

 academic

0.39

 students

0.38

成绩

0.38

 graduated

0.37

 Student

0.34

 Academic

0.34

 réussite

0.33

Activations Density 0.171%

numeric values related to exam scores and their derived calculations

No Comments

No Known Activations