INDEX

Explanations

references to rewards or bonuses in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

gev

-0.40

mgp

-0.37

HtmlAttribute

-0.36

Santis

-0.36

pexpr

-0.35

 cejas

-0.34

getActiveSheet

-0.33

[]

-0.32

illants

-0.32

 expanding

-0.32

POSITIVE LOGITS

 bite

0.95

 kissed

0.86

 Bonus

0.84

 deduction

0.84

 Bite

0.84

 bites

0.83

bonus

0.83

 bonus

0.81

 defects

0.81

vitamin

0.81

Activations Density 0.238%

references to rewards or bonuses in various contexts

No Comments

No Known Activations