INDEX

Explanations

references to specific software components or libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 henvisninger

-0.63

aarrggbb

-0.53

 overras

-0.48

 تكبرها

-0.48

føre

-0.47

alaya

-0.45

 Linear

-0.44

 fermée

-0.43

 ilmiah

-0.43

 biologique

-0.43

POSITIVE LOGITS

NameInMap

0.78

DebuggerNonUser

0.77

 NSCoder

0.77

 protoimpl

0.75

ngdoc

0.69

Билгалдахарш

0.66

GIVEREF

0.65

__(/*!

0.64

MemoryWarning

0.63

Hochspringen

0.62

Activations Density 0.113%

references to specific software components or libraries

No Comments

No Known Activations