INDEX

Explanations

negations and indications of absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 only

-0.89

only

-0.73

ONLY

-0.72

 ONLY

-0.66

Only

-0.63

 только

-0.57

 chiunque

-0.56

 saja

-0.56

 uniquement

-0.53

 tylko

-0.52

POSITIVE LOGITS

 nakalista

0.94

 betweenstory

0.93

Personensuche

0.82

AndEndTag

0.78

 صوتيه

0.77

 defaultstate

0.77

ValueStyle

0.77

 initComponents

0.75

Yet

0.74

ंदीखरीदारी

0.73

Activations Density 0.327%

negations and indications of absence

No Comments

No Known Activations