INDEX

Explanations

terms related to licensing and certification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Curves

-0.64

 Advis

-0.56

 predecessor

-0.55

ificent

-0.55

gestone

-0.53

 mace

-0.53

 Jayne

-0.53

 curves

-0.53

[],

-0.52

 équipe

-0.51

POSITIVE LOGITS

flush

0.83

 flush

0.73

Datuak

0.68

Flush

0.67

$.

0.63

 licence

0.63

mű

0.62

 deeply

0.61

 Flush

0.59

 profoundly

0.59

Activations Density 0.124%

terms related to licensing and certification

No Comments

No Known Activations