INDEX

Explanations

words and phrases related to immersion and involvement in experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

SharedCtor

-0.65

setMsg

-0.65

DNEY

-0.64

Alexandre

-0.64

 McNeil

-0.64

 Krebs

-0.63

 Haas

-0.63

\#:

-0.62

ˈ

-0.61

nej

-0.61

POSITIVE LOGITS

 itſelf

1.01

 therein

0.97

in

0.94

 AssemblyCulture

0.93

 himſelf

0.93

 myſelf

0.92

SpringRunner

0.88

 purpoſe

0.86

Sucesor

0.86

InputBorder

0.85

Activations Density 0.652%

words and phrases related to immersion and involvement in experiences

No Comments

No Known Activations