INDEX

Explanations

terms related to stimulation or activation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

MigrationBuilder

-0.51

ab

-0.50

ex

-0.48

Apo

-0.46

hon

-0.46

 aspir

-0.46

Ros

-0.46

ad

-0.46

Ry

-0.46

Vors

-0.45

POSITIVE LOGITS

Stim

0.76

 stimulates

0.74

 stimulate

0.74

 stimulated

0.73

 stimulating

0.67

 estímulo

0.65

 Stimulus

0.63

 estimular

0.63

 Stim

0.63

 stimulation

0.59

Activations Density 0.162%

terms related to stimulation or activation in various contexts

No Comments

No Known Activations