INDEX

Explanations

terms related to evidence and verification in scientific arguments

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

esgue

-0.55

SourceChecksum

-0.55

calciatore

-0.52

 AssemblyVersion

-0.51

GraphicsUnit

-0.51

DockStyle

-0.49

EFIAPI

-0.47

########.

-0.47

 IBOutlet

-0.46

 اطلع

-0.46

POSITIVE LOGITS

rrggbb

0.66

 cherchés

0.57

 judging

0.56

 assertions

0.55

 assertion

0.55

AntiForgeryToken

0.52

 claim

0.52

assertions

0.51

 féd

0.51

 décontract

0.51

Activations Density 0.795%

terms related to evidence and verification in scientific arguments

No Comments

No Known Activations