INDEX

Explanations

recognitions and realizations related to personal reflections or insights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.46

 quoque

-0.46

樣的

-0.43

 cuerdas

-0.41

 odeur

-0.41

 giang

-0.41

 themſelves

-0.41

 desmotivaciones

-0.40

 dezelve

-0.40

 uits

-0.40

POSITIVE LOGITS

 realization

1.75

 realize

1.67

 realizing

1.57

 realisation

1.53

 realized

1.53

 realizes

1.53

 realise

1.48

 realiz

1.38

 realising

1.37

 realises

1.34

Activations Density 0.121%

recognitions and realizations related to personal reflections or insights

No Comments

No Known Activations