INDEX

Explanations

references to cognitive test scores and assessments in relation to neurological conditions

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

AndEndTag

-0.77

principalColumn

-0.69

 kaarangay

-0.68

OGND

-0.68

tagHelperRunner

-0.68

EndContext

-0.63

 Chwiliwch

-0.59

 Мексичка

-0.59

ftagPool

-0.58

SequentialGroup

-0.58

POSITIVE LOGITS

 into

0.33

Conse

0.33

ec

0.31

ary

0.30

 Rade

0.30

ToObject

0.30

 fate

0.30

vos

0.30

 barba

0.30

madi

0.29

Activations Density 1.656%

references to cognitive test scores and assessments in relation to neurological conditions

No Comments

No Known Activations