INDEX

Explanations

references to research findings and results

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

دانشنامهٔ

-0.65

Personensuche

-0.55

 kasarigan

-0.55

يميديا

-0.52

 مرئيه

-0.47

 الرياضيه

-0.47

irtschaft

-0.45

 ویکی‌پدیا

-0.44

shid

-0.44

 nouve

-0.43

POSITIVE LOGITS

 performed

0.73

 obtained

0.72

 realizadas

0.69

 undertaken

0.69

obtained

0.68

Performed

0.67

 unsuccessful

0.65

經過

0.65

 conducted

0.65

MIDDLEWARE

0.64

Activations Density 0.515%

references to research findings and results

No Comments

No Known Activations