INDEX

Explanations

numerical values related to statistics or votes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CodeAttribute

-0.69

adaptiveStyles

-0.69

étit

-0.67

Scénario

-0.67

 EconPapers

-0.66

ConstraintMaker

-0.66

EndTag

-0.65

 فريبيس

-0.65

EDEFAULT

-0.64

EndContext

-0.62

POSITIVE LOGITS

枠

0.54

 four

0.48

 slots

0.46

 hiszen

0.45

 pianta

0.42

 maximum

0.42

 faute

0.41

الإنجليزية

0.41

 five

0.41

 belanja

0.41

Activations Density 0.451%

numerical values related to statistics or votes

No Comments

No Known Activations