INDEX

Explanations

expressions of willingness or readiness to take action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Fournier

-0.86

 Dunbar

-0.77

<b>

-0.76

 Koll

-0.75

 Cutler

-0.72

Phal

-0.72

 Blackman

-0.71

IPR

-0.70

 McNeil

-0.67

Linq

-0.66

POSITIVE LOGITS

 PLWABN

0.92

]`

0.90

)}

0.90

 ExecuteAsync

0.88

 Murch

0.85

parsedMessage

0.85

Lem

0.84

 بيها

0.83

 متعلقه

0.83

)':

0.83

Activations Density 0.434%

expressions of willingness or readiness to take action

No Comments

No Known Activations