INDEX

Explanations

statements indicating true/false values or exploring queries related to conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

########.

-0.72

makeConstraints

-0.66

TestingModule

-0.64

XmlSchema

-0.64

onAttach

-0.61

StoryboardSegue

-0.59

tagHelperRunner

-0.59

AnchorStyles

-0.57

ftagPool

-0.55

ConstraintMaker

-0.55

POSITIVE LOGITS

Ծանոթ

0.66

 különböz

0.58

 bénévoles

0.56

 terakhir

0.50

 vérit

0.49

 prisonniers

0.49

 kyllä

0.48

 façons

0.48

 llantas

0.48

 længere

0.48

Activations Density 2.772%

statements indicating true/false values or exploring queries related to conditions

No Comments

No Known Activations