INDEX

Explanations

words indicating numerical values or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

parsedMessage

-1.46

+#+#

-1.39

StoryboardSegue

-1.38

^(@)

-1.34

 Roskov

-1.30

MigrationBuilder

-1.30

SharedCtor

-1.29

tagHelperRunner

-1.29

ChildScrollView

-1.26

ItemBackground

-1.25

POSITIVE LOGITS

↵

0.80

0.74

↵↵

0.73

0.62

0.59

0.58

0.57

↵↵↵

0.57

Activations Density 1.397%

words indicating numerical values or quantities

No Comments

No Known Activations