INDEX

Explanations

references to different types of events, especially in a mathematical or scientific context

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

)">

-0.85

mapStateToProps

-0.82

 navegando

-0.80

])),

-0.79

uttosto

-0.79

 figliu

-0.78

 Viber

-0.78

])]

-0.77

 zufolge

-0.77

 }}$}

-0.77

POSITIVE LOGITS

 events

2.17

 event

2.03

 Events

1.84

events

1.78

 Event

1.76

 EVENTS

1.70

Events

1.66

 EVENT

1.65

event

1.60

Event

1.50

Activations Density 0.056%

references to different types of events, especially in a mathematical or scientific context

No Comments

No Known Activations