INDEX

Explanations

terms related to artificial neural networks and their methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

 Roskov

-0.57

-0.53

httphttps

-0.50

twimg

-0.46

tanleria

-0.45

Tembelea

-0.44

 Wikimedijinoj

-0.44

tvguidetime

-0.43

ruik

-0.41

 nakalista

-0.41

POSITIVE LOGITS

 process

0.53

 solution

0.52

 retrieve

0.50

 Maximum

0.48

 parameter

0.47

 ObjectParameter

0.47

 Operating

0.47

 criteria

0.47

 component

0.47

 parameters

0.47

Activations Density 0.919%

terms related to artificial neural networks and their methodologies

No Comments

No Known Activations