INDEX

Explanations

terms related to profits and profitability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Saty

-0.78

 Eureka

-0.76

getHeaders

-0.76

 Seminary

-0.74

Eureka

-0.73

rature

-0.73

YLON

-0.73

 vectorielle

-0.71

 Duckworth

-0.71

MSR

-0.70

POSITIVE LOGITS

profit

2.27

 Profit

2.06

Profit

2.06

 profit

2.03

profits

1.55

 profits

1.43

 nonprofit

1.40

 Profits

1.36

 PROF

1.31

 Nonprofit

1.17

Activations Density 0.052%

terms related to profits and profitability

No Comments

No Known Activations