INDEX

Explanations

references to blindness, both literal and metaphorical

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

cshtml

-0.81

WebElementEntity

-0.77

nextProps

-0.65

SerializeField

-0.60

ArgsConstructor

-0.59

ิลปะ

-0.59

 jPanel

-0.57

\{\\

-0.56

RefNanny

-0.55

 CoreData

-0.53

POSITIVE LOGITS

folded

0.99

Blind

0.68

folds

0.67

 blinds

0.64

fold

0.64

 Blind

0.63

 Catawiki

0.63

 otomatig

0.63

deaf

0.61

sided

0.61

Activations Density 0.108%

references to blindness, both literal and metaphorical

No Comments

No Known Activations