INDEX

Explanations

structured data elements or formats, particularly in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Kov

-0.61

 Gould

-0.60

TextFormField

-0.58

Zed

-0.57

 Bial

-0.56

Maz

-0.54

 Gibbon

-0.53

 Motta

-0.53

 atendido

-0.52

 عاش

-0.52

POSITIVE LOGITS

BeginInit

0.79

 Normdatei

0.79

Rhestr

0.77

HasForeignKey

0.76

]")]

0.76

."</

0.74

">//

0.73

ToScroll

0.72

tableFuture

0.71

`}

0.71

Activations Density 0.077%

structured data elements or formats, particularly in a coding context

No Comments

No Known Activations