INDEX

Explanations

references to sections and organization within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 bort

-0.53

ня

-0.48

 Corp

-0.48

Du

-0.48

 CORPORATION

-0.48

 bety

-0.47

inem

-0.46

yntaxException

-0.46

UIM

-0.46

 Growers

-0.46

POSITIVE LOGITS

BeginInit

0.88

InjectAttribute

0.79

UnknownFields

0.72

webElementXpaths

0.67

 تضيفلها

0.67

 mxArray

0.66

 Majefty

0.66

 chapters

0.66

IsContent

0.66

 autorytatywna

0.65

Activations Density 0.440%

references to sections and organization within documents

No Comments

No Known Activations