INDEX

Explanations

specific medical terms and their associated parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 Monfieur

-0.59

 AssemblyTitle

-0.58

 utafitiHapana

-0.57

 queſta

-0.56

 Roskov

-0.55

ніципалі

-0.52

 Italijani

-0.52

GEBURTSDATUM

-0.52

saco

-0.51

TagMode

-0.50

POSITIVE LOGITS

 nakalista

0.69

 NSCoder

0.40

 ComVisible

0.39

 defaultstate

0.38

setVerticalGroup

0.35

masti

0.35

useEffect

0.34

ことはない

0.34

ss

0.32

MemoryWarning

0.32

Activations Density 0.497%

specific medical terms and their associated parameters

No Comments

No Known Activations