INDEX

Explanations

proper nouns, specifically names of people

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



-0.68

randomUUID

-0.66

 Mistress

-0.64

fő

-0.63

strerror

-0.63

 côtés

-0.62

rimid

-0.60

 oreilles

-0.60

 gräns

-0.59

 وتسجيلات

-0.58

POSITIVE LOGITS

("%.

0.75

PhysRev

0.74

fucking

0.69

andescent

0.69

idopsis

0.68

Ed

0.67

 Seeder

0.66

,:,

0.65

PerformLayout

0.65

djangoproject

0.62

Activations Density 0.706%

proper nouns, specifically names of people

No Comments

No Known Activations