INDEX

Explanations

references to programming constructs and data structures

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

expandindo

-0.53

AccessorTable

-0.46

oprot

-0.44

vela

-0.43

ophon

-0.42

kkelen

-0.41

rogen

-0.40

permitAll

-0.40

 wrecks

-0.39

atter

-0.39

POSITIVE LOGITS

 مواليد

0.78

NameInMap

0.71

$_['

0.70

 الدولى

0.69

 ſta

0.69

 houſe

0.68

 समीक्षाओं

0.67

apnews

0.66

seamnă

0.66

 dafs

0.65

Activations Density 0.237%

references to programming constructs and data structures

No Comments

No Known Activations