INDEX

Explanations

references and mentions of completeness or totality across various contexts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

bouncycastle

-0.54

geth

-0.46

 Mede

-0.45

ratore

-0.44

miot

-0.44

timus

-0.44

 gero

-0.43

Mer

-0.43

times

-0.43

онов

-0.42

POSITIVE LOGITS

 protoimpl

0.85

Искәрмәләр

0.85

Билгалдахарш

0.84



0.84

Források

0.78

 Wikimedijinoj

0.75

Dữ

0.75

Jegyzetek

0.72

QMetaType

0.71

setVerticalGroup

0.71

Activations Density 0.281%

references and mentions of completeness or totality across various contexts

No Comments

No Known Activations