INDEX

Explanations

terms related to representation and authority

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

 OkHttpClient

-0.71

XtraEditors

-0.69

 peines

-0.68

 onPostExecute

-0.67

 Civil

-0.63

pfel

-0.62

omány

-0.62

issues

-0.62

slidesToShow

-0.61

chaikovsky

-0.60

POSITIVE LOGITS

 Representations

1.39

 representations

1.38

 representing

1.33

 representation

1.31

 Represents

1.29

 REPRESENT

1.28

 Represent

1.28

Represent

1.27

 represents

1.27

 Representation

1.26

Activations Density 0.117%

terms related to representation and authority

No Comments

No Known Activations