INDEX

Explanations

references to authors and their work

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 these

-0.45

 المعيارى

-0.42

 this

-0.42

 more

-0.41

口碑

-0.41

Filmografie

-0.41

 hierdie

-0.40

více

-0.39

WriteBarrier

-0.39

ómicas

-0.38

POSITIVE LOGITS

 admin

1.03

admin

1.00

 Admin

0.98

 Administrator

0.96

 ADMIN

0.89

Personendaten

0.84

tvguidetime

0.83

Admin

0.82

 administrator

0.81

ADMIN

0.80

Activations Density 0.077%

references to authors and their work

No Comments

No Known Activations