INDEX

Explanations

terms and references related to coding libraries and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Autoritní

-0.96

endphp

-0.95

ագրություններ

-0.88

évaluateur

-0.82

 سكانية

-0.80



-0.78

paravant

-0.75

 Wiktionnaire

-0.75

 beginnetje

-0.72

 للمعارف

-0.72

POSITIVE LOGITS

ComponentModel

0.61

royal

0.60

andi

0.55

zec

0.54

 Cornelius

0.54

endl

0.54

 Ivan

0.53

надца

0.52

anda

0.52

Ali

0.52

Activations Density 2.818%

terms and references related to coding libraries and data structures

No Comments

No Known Activations