INDEX

Explanations

mathematical expressions related to graph theory

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

-0.61

two

-0.61

 development

-0.60

 cross

-0.60

 physical

-0.58

 target

-0.57

↵↵

-0.57

 high

-0.55

pre

-0.54

 success

-0.54

POSITIVE LOGITS

StoryboardSegue

1.15

enumi

1.09

 Exacts

1.04

ConstraintMaker

1.03

 Normdatei

0.99

IsMutable

0.99

 AssemblyProduct

0.99

 protoimpl

0.98

 ComVisible

0.97

UpInside

0.97

Activations Density 1.120%

mathematical expressions related to graph theory

No Comments

No Known Activations