INDEX

Explanations

terms related to nerve function and injury

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

cipar

-0.46

 cheeks

-0.45

ropshire

-0.44

mouth

-0.44

 Hause

-0.43

oč

-0.42

vair

-0.41

objPHPExcel

-0.41

شهاد

-0.41

Pers

-0.41

POSITIVE LOGITS

 nerve

1.16

 Nerve

1.08

 Nerven

0.96

 nerves

0.89

 neurons

0.87

 neurological

0.81

 neuron

0.81

神经

0.76

 neuro

0.75

 affer

0.74

Activations Density 1.403%

terms related to nerve function and injury

No Comments

No Known Activations