INDEX

Explanations

references to movies and their awards or recognitions

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

djangoproject

-0.57

centralwidget

-0.53

 comedy

-0.50

 risa

-0.48

 déli

-0.48

 Crocker

-0.47

DECREF

-0.47

 Betty

-0.46

 MainAxisSize

-0.46

POSITIVE LOGITS

 glau

0.74

Geplaatst

0.74

StoryboardSegue

0.73

 oprot

0.70

 Hunger

0.69

 <=",

0.65

Obrázky

0.61

Hunger

0.60

 esternos

0.58

 Gaul

0.58

Activations Density 0.110%

references to movies and their awards or recognitions

No Comments

No Known Activations