INDEX

Explanations

references to income-related concepts and terms in financial 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 @ 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

 düğ

-0.42

ItemIndex

-0.42

Iz

-0.41

truly

-0.41

 brief

-0.40

 вру

-0.37

Trial

-0.37

 nails

-0.36

 makers

-0.36

Vaz

-0.36

POSITIVE LOGITS

 income

1.88

 Income

1.73

Income

1.69

 revenue

1.69

income

1.66

 INCOME

1.58

 Revenue

1.49

Revenue

1.47

revenue

1.45

 revenues

1.44

Activations Density 0.203%

references to income-related concepts and terms in financial contexts

No Comments

No Known Activations