INDEX

Explanations

prepositions and phrases indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 aspects

-0.70

 Normdatei

-0.61

various

-0.56

 processes

-0.53

 purposes

-0.52

 various

-0.52

Enllaces

-0.52

 examples

-0.49

 methods

-0.48

aspects

-0.48

POSITIVE LOGITS

)++;

0.93

 existence

0.87

 success

0.75

existence

0.74

PMailer

0.72

 needing

0.70

InjectAttribute

0.70

StoreMessageInfo

0.69

 obtaining

0.68

 للمعارف

0.68

Activations Density 0.567%

prepositions and phrases indicating relationships or connections

No Comments

No Known Activations