INDEX

Explanations

terms related to downloadable products and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

GeoNames

-0.47

webElementGuid

-0.47

bitField

-0.46

 rynku

-0.43

 bowiem

-0.40

 elettrico

-0.40

GIVEREF

-0.40

 jdbcTemplate

-0.38

 CURIAM

-0.38

 doccia

-0.37

POSITIVE LOGITS

+#+#

0.47

exitRule

0.46

plom

0.45

udy

0.44

 Realistic

0.44

onge

0.44

diz

0.43

 Result

0.42

 Photocase

0.42

 Possible

0.42

Activations Density 1.848%

terms related to downloadable products and services

No Comments

No Known Activations