INDEX

Explanations

specific queries, commands, and parameters within technical documentation or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

+#+#

-0.57

 للمعارف

-0.51

parsedMessage

-0.50

inSlope

-0.49

✭✭

-0.48

 Administrativna

-0.48

 dAtA

-0.47

цездатний

-0.47

 Signalez

-0.46

endpush

-0.46

POSITIVE LOGITS

ⓧ

0.50

RTLI

0.42

MigrationBuilder

0.41

slidesToShow

0.40

………………………………

0.40

 defaultstate

0.39

 Northern

0.38

ApiOperation

0.37

 ProtoMessage

0.36

aminen

0.36

Activations Density 0.052%

specific queries, commands, and parameters within technical documentation or programming contexts

No Comments

No Known Activations