INDEX

Explanations

phrases emphasizing benefits and positive outcomes, particularly in contexts related to support, efficiency, and personal growth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.82

 Савезне

-0.75

 myſelf

-0.73

uxxxx

-0.71

 resourceCulture

-0.71

ſelves

-0.71

featureID

-0.71

]--;

-0.69

 للمعارف

-0.69

MENAFN

-0.69

POSITIVE LOGITS

 navíc

0.55

benef

0.54

fun

0.52

又能

0.51

uits

0.50

 benefits

0.50

 benefit

0.49

usehen

0.49

 plus

0.47

 saves

0.46

Activations Density 0.274%

phrases emphasizing benefits and positive outcomes, particularly in contexts related to support, efficiency, and personal growth

No Comments

No Known Activations