INDEX

Explanations

references to systematic processes or methodologies

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

ंदीखरीदारी

-0.59

 favor

-0.56

SceneManagement

-0.55

rhosis

-0.54

 rowspan

-0.52

 honor

-0.51

Quin

-0.50

 points

-0.50

 expansion

-0.49

POSITIVE LOGITS

 superiori

0.79

 espagne

0.78

 systematically

0.78

ſelves

0.77

Systematic

0.77

ſelf

0.77

 neceffary

0.76

 Jefus

0.76

Beijos

0.75

 Anſ

0.75

Activations Density 0.106%

references to systematic processes or methodologies

No Comments

No Known Activations