INDEX

Explanations

citations and references formatted for academic articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 виправивши

-1.02

دانشنامهٔ

-0.93

 beginnetje

-0.90

 Италијани

-0.85

keyColumn

-0.75

 tartalomajánló

-0.74

 Autorisations

-0.72

 utafitiHapana

-0.71

 Exacts

-0.71

 raiſ

-0.70

POSITIVE LOGITS

مراجع

0.73

 BoxDecoration

0.61

المراجع

0.58

springframework

0.57

igslist

0.56

 unittest

0.56

 تعدى

0.55

 MonoBehaviour

0.54

makeText

0.53

PRNewswire

0.51

Activations Density 0.090%

citations and references formatted for academic articles

No Comments

No Known Activations