INDEX

Explanations

references to significant events or actions 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SharedDtor

-0.88

 disambiguazione

-0.76

 BoxFit

-0.75

 pinulongan

-0.74

 uner

-0.71

 intptr

-0.70

 VizieR

-0.68

WithIOException

-0.68

elux

-0.67

webElementGuid

-0.66

POSITIVE LOGITS

__":

0.67

This

0.66

 jointly

0.58

 This

0.53

此次

0.53

this

0.50

这也

0.50

eraard

0.49

 this

0.49

]";

0.46

Activations Density 0.228%

references to significant events or actions in various contexts

No Comments

No Known Activations