INDEX

Explanations

proper nouns and names of individuals, often in a biographical context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 للمعارف

-0.56

 nahilalakip

-0.54

.*")]

-0.53

 createStore

-0.52

‍♂️

-0.52

 nakalista

-0.50

AddHtmlAttribute

-0.47

ConstraintMaker

-0.46

 getItemCount

-0.45

sizeCache

-0.44

POSITIVE LOGITS

 funding

0.41

 muft

0.39

CGPoint

0.38

phosa

0.37

balleur

0.36

 dévou

0.36

évé

0.34

 Funding

0.34

 vectorielles

0.34

 سبيل

0.34

Activations Density 0.386%

proper nouns and names of individuals, often in a biographical context

No Comments

No Known Activations