INDEX

Explanations

terms related to synaptic mechanisms and plasticity processes 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

таратура

-0.60

psack

-0.60

fjspx

-0.58

kloped

-0.57

 المعيارى

-0.56

 LiveData

-0.55

DataAnnotations

-0.55

 Gregorian

-0.53

 snippetHide

-0.53

 فريبيس

-0.52

POSITIVE LOGITS

 synaptic

0.95

 synapses

0.95

 synapse

0.87

 neuronal

0.84

 neurons

0.80

 neuron

0.80

 firing

0.74

 neuro

0.72

 excit

0.72

 Neurosci

0.72

Activations Density 1.265%

terms related to synaptic mechanisms and plasticity processes in the brain

No Comments

No Known Activations