INDEX

Explanations

statements regarding evaluations or assessments in a research or legal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ftagPool

-0.82

apimachinery

-0.75

ⓧ

-0.74

 Meksiku

-0.74

 OFDb

-0.74

djangoproject

-0.71

aarrggbb

-0.67

 Мексичка

-0.67

 gradova

-0.65

PreInfinity

-0.65

POSITIVE LOGITS

tagHelperRunner

0.54

脚注の使い方

0.53

endphp

0.51

AutoresizingMask

0.51

(!__

0.47

IERRA

0.46

 snippetHide

0.45

ATEGY

0.45

ksessa

0.45

 thiệu

0.45

Activations Density 4.435%

statements regarding evaluations or assessments in a research or legal context

No Comments

No Known Activations