INDEX

Explanations

references to events in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 insuffisamment

-0.73

mapStateToProps

-0.73

])]

-0.71

 navegando

-0.70

 Viber

-0.69

 figliu

-0.69

utnik

-0.69

 ladri

-0.69

)">

-0.68

fich

-0.68

POSITIVE LOGITS

 events

2.07

 event

1.89

 Events

1.75

events

1.69

 Event

1.68

 EVENTS

1.64

 EVENT

1.58

Events

1.57

event

1.49

Event

1.40

Activations Density 0.068%

references to events in various contexts

No Comments

No Known Activations