INDEX

Explanations

phrases indicating lists or summaries of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

=?,

-0.50

 dagegen

-0.49

Portale

-0.49

''}

-0.47

 ویکی‌پدیا

-0.46

kto

-0.46

Somehow

-0.46

PDOException

-0.46

ArrowToggle

-0.46

GEBURTSDATUM

-0.45

POSITIVE LOGITS

 following

2.48

following

2.19

 follows

2.08

 Following

1.98

Following

1.87

 follow

1.83

 FOLLOWING

1.72

follows

1.66

 siguiente

1.63

 siguientes

1.62

Activations Density 0.289%

phrases indicating lists or summaries of information

No Comments

No Known Activations