INDEX

Explanations

phrases related to control and influence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

igslist

-0.53

 acceptability

-0.48

fört

-0.48

initComponents

-0.48

 picioare

-0.47

으로

-0.46

المراجع

-0.46

庁

-0.46

ністю

-0.45

tahankan

-0.45

POSITIVE LOGITS

DoubleQuotes

0.73

 Roskov

0.71

 propOrder

0.64

 AssemblyCompany

0.63

SharedDtor

0.62

исленность

0.60

={({

0.56

orianCalendar

0.56

EndContext

0.55

 препратки

0.55

Activations Density 0.855%

phrases related to control and influence in various contexts

No Comments

No Known Activations