INDEX

Explanations

keywords and phrases indicating relationships or connections

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 settlers

-0.49

 arbitrators

-0.48



-0.48

cluye

-0.47

variable

-0.47

charpe

-0.46

 ActivatedRoute

-0.46

 bestanden

-0.44

 formulations

-0.44

lapsingToolbar

-0.44

POSITIVE LOGITS

 تضيفلها

0.87

 Signalez

0.76

istoitu

0.73

InjectAttribute

0.71

новниш

0.67

contentLoaded

0.64

Kilder

0.63

Hochspringen

0.61

 linkovi

0.60

 nakalista

0.60

Activations Density 0.857%

keywords and phrases indicating relationships or connections

No Comments

No Known Activations