INDEX

Explanations

sentences containing figures, diagrams, or schematic representations

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

✭✭

-0.54

↵

-0.52

Sabah

-0.48

 souci

-0.48

 ddelweddau

-0.47

dropna

-0.47

zeň

-0.47

زیک

-0.47

Osp

-0.46

usda

-0.46

POSITIVE LOGITS

 autorytatywna

0.80

Portale

0.75

kloped

0.74

migrationBuilder

0.73

Autoritní

0.73

最快更新

0.72

✨:

0.72

脚注の使い方

0.69

 jsPsych

0.69

Bibliograf

0.68

Activations Density 0.227%

sentences containing figures, diagrams, or schematic representations

No Comments

No Known Activations