INDEX

Explanations

terms related to keyboards

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

 apparently

-0.62

<?

-0.56

Apparently

-0.55

beforeAll

-0.55

apparently

-0.53

戚

-0.52

ville

-0.50

mine

-0.49

times

-0.48

 Apparently

-0.48

POSITIVE LOGITS

 badge

0.90

 credentials

0.85

 badges

0.81

 Kent

0.76

 Badge

0.75

 keyboard

0.73

 keyboards

0.73

 Credentials

0.72

 betweenstory

0.71

URLException

0.71

Activations Density 0.074%

terms related to keyboards

No Comments

No Known Activations