INDEX

Explanations

concepts related to visual information processing and memory in the brain

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

worthiness

-0.49

...

-0.48

essional

-0.47

 continúas

-0.46

 following

-0.45

 rigor

-0.43

σιμο

-0.43

GORITHM

-0.43

SWIG

-0.43

POSITIVE LOGITS

 Мексичка

0.78

 NSCoder

0.72

 sensory

0.71

 Perception

0.69

 perception

0.67

 sensorial

0.64

 táctil

0.64

didSet

0.63

providedIn

0.63

 définiti

0.63

Activations Density 0.423%

concepts related to visual information processing and memory in the brain

No Comments

No Known Activations