INDEX

Explanations

numerical data and measurements related to studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IsContent

-0.86

مصادر

-0.69

 angelo

-0.68

 ervoor

-0.67

 Billings

-0.67

 يتيمه

-0.67

Kuch

-0.66

XtraGrid

-0.66

ISupport

-0.66

Muri

-0.66

POSITIVE LOGITS

subsection

1.10

subsubsection

0.91

ViewFeatures

0.74

Mö

0.69

따

0.64

kowym

0.64

 Bang

0.63

FTE

0.62

httphttps

0.62

COHOL

0.62

Activations Density 0.662%

numerical data and measurements related to studies

No Comments

No Known Activations