INDEX

Explanations

references to openings and seals in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

rungsseite

-0.67

 تضيفلها

-0.58

 ProtoMessage

-0.55

bollah

-0.54

Personensuche

-0.54

 gynhyrchwyd

-0.54

ContentLoaded

-0.53

TypedDataSet

-0.53



-0.53

NameInMap

-0.52

POSITIVE LOGITS

 opening

1.04

 openings

1.01

 ouverture

0.83

opening

0.82

 apertures

0.80

 opened

0.80

 hole

0.78

Opening

0.78

 öpp

0.78

 Opening

0.77

Activations Density 0.556%

references to openings and seals in various contexts

No Comments

No Known Activations