INDEX

Explanations

references to relationships and connections with others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 themſelves

-0.50

 saddles

-0.49

 itſelf

-0.47

 Beide

-0.47

 οπο

-0.46

rootNode

-0.45

 Автор

-0.43

rot

-0.43

 keduanya

-0.43

대로

-0.43

POSITIVE LOGITS

 fellow

1.23

 peers

1.01

fellow

1.01

 colleagues

0.98

 teammate

0.95

 rivals

0.90

Fellow

0.90

 colleague

0.90

 partner

0.89

 mates

0.88

Activations Density 0.220%

references to relationships and connections with others

No Comments

No Known Activations