INDEX

Explanations

references to starting or initiating actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 OFDb

-0.99

Хьажоргаш

-0.98

]--;

-0.92

 للمعارف

-0.90

:✨

-0.87

 تضيفلها

-0.83

bootstrapcdn

-0.83

XmlAccessorType

-0.82

Efq

-0.82

 كومونز

-0.81

POSITIVE LOGITS

 starters

0.56

 starter

0.55

 startup

0.51

STARTED

0.50

 initial

0.49

 Startup

0.46

スタート

0.46

STARTING

0.45

ller

0.45

 START

0.45

Activations Density 0.207%

references to starting or initiating actions

No Comments

No Known Activations