INDEX

Explanations

instances of medical or technical jargon related to integrated circuits and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 autorytatywna

-0.89

RectangleBorder

-0.85

ViewImports

-0.84

CloseOperation

-0.80

Personendaten

-0.72

::::::::

-0.70

 tartalomajánló

-0.70

ktop

-0.70

 跳转至

-0.69

 AssemblyCulture

-0.68

POSITIVE LOGITS

 iArr

0.58

 pinggang

0.57

 ulang

0.48

Ivoire

0.48

 iVar

0.47

Ier

0.47

 gratification

0.45

ydable

0.45

 veille

0.45

reviewed

0.45

Activations Density 0.283%

instances of medical or technical jargon related to integrated circuits and their properties

No Comments

No Known Activations