INDEX

Explanations

elements related to product descriptions and visual representations

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

borderFill

-0.41

 hospod

-0.39

危險

-0.36

 confira

-0.36

OrNil

-0.36

ViewChild

-0.35

危险

-0.35

 Umum

-0.34

galkan

-0.34

ecap

-0.34

POSITIVE LOGITS

 SafeMath

0.50

 brochures

0.49

StoryboardSegue

0.47

 marketing

0.47

featureID

0.46

 thiệu

0.46

 sales

0.46

 salespeople

0.45

 descriptions

0.45

 salesperson

0.45

Activations Density 0.037%

elements related to product descriptions and visual representations

No Comments

No Known Activations