INDEX

Explanations

keywords related to software components and properties within programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 fatte

-0.49

 faite

-0.48

 constaté

-0.48

in

-0.46

GETHER

-0.45

 form

-0.43

 here

-0.42

Substance

-0.42

madas

-0.42

POSITIVE LOGITS

verwijspagina

0.79

ItemBackground

0.78

 Majefty

0.75

)";

0.71

 reaſon

0.69

AnchorStyles

0.68

Efq

0.67

 TÉCN

0.66

ValueStyle

0.66

 itſelf

0.65

Activations Density 2.115%

keywords related to software components and properties within programming contexts

No Comments

No Known Activations