INDEX

Explanations

terms related to recognition and acknowledgment of rights and contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

eb

-0.35

Spoljašnje

-0.34

loot

-0.34

Il

-0.33

 merrily

-0.33

Fl

-0.33

lot

-0.33

Dyn

-0.33

疱

-0.33

Cost

-0.32

POSITIVE LOGITS

 recognition

2.17

 Recognition

2.05

 recognize

2.02

 recognizes

1.95

recognition

1.95

 recognized

1.94

 RECOGN

1.93

Recognition

1.92

 recognizing

1.90

recognize

1.89

Activations Density 0.116%

terms related to recognition and acknowledgment of rights and contributions

No Comments

No Known Activations