INDEX

Explanations

terms related to NMDA receptors and long-term depression (LTD) in neural contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

riezmann

-0.75

出版年

-0.74

 GeoNames

-0.68

NewUrlParser

-0.68

ussis

-0.66

cillors

-0.66

SaveChangesAsync

-0.66

softc

-0.65

Droid

-0.65

 bVar

-0.64

POSITIVE LOGITS

 glutamate

0.94

 gluta

0.66

 espin

0.58

 EdgeInsets

0.56

IsRequired

0.54

 roli

0.53

 madres

0.51

GL

0.49

hfill

0.48

 excit

0.48

Activations Density 0.009%

terms related to NMDA receptors and long-term depression (LTD) in neural contexts

No Known Activations