INDEX

Explanations

references to security features and access points of properties

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

tvguidetime

-0.81

AndEndTag

-0.58

ImageContext

-0.55

rzost

-0.54

Tembelea

-0.52

usermodel

-0.51

 BoxDecoration

-0.50

 endblock

-0.50

 Rohr

-0.49

 jails

-0.48

POSITIVE LOGITS

 entrance

1.90

 Entrance

1.66

 entry

1.60

 entrances

1.60

entrance

1.53

Entrance

1.47

 Entry

1.46

Entry

1.34

 entrada

1.33

entry

1.31

Activations Density 0.120%

references to security features and access points of properties

No Comments

No Known Activations