INDEX

Explanations

openers indicating the beginning of significant text sections

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

DeleteBehavior

-0.71

GEBURTSDATUM

-0.71

хьтан

-0.58

 Wicidata

-0.57

)))));

-0.55

Vidite

-0.55

 NSCoder

-0.54

AccessorTable

-0.54

featureID

-0.53

SharedDtor

-0.51

POSITIVE LOGITS

期刊论文

0.56

 puissent

0.54

ruitment

0.53

 InputDecoration

0.52

 Exacts

0.51

̓

0.50

 TAMBIÉN

0.49

 Labeling

0.48

 campana

0.48

conectar

0.48

Activations Density 0.035%

openers indicating the beginning of significant text sections

No Comments

No Known Activations