INDEX

Explanations

terms related to "event" and its various attributes or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

mapStateToProps

-0.75

 insuffisamment

-0.75

 figliu

-0.74

)">

-0.73

 navegando

-0.73

fich

-0.73

 zufolge

-0.73

 Theſe

-0.72

 Viber

-0.72

 ladri

-0.71

POSITIVE LOGITS

 events

2.11

 event

1.96

 Events

1.80

 Event

1.74

events

1.73

 EVENTS

1.68

 EVENT

1.63

Events

1.60

event

1.54

Event

1.44

Activations Density 0.057%

terms related to "event" and its various attributes or occurrences

No Comments

No Known Activations