INDEX

Explanations

function calls related to setting and adding properties or nodes in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 disambiguazione

-0.79

principalColumn

-0.75

 Theſe

-0.68

 الحره

-0.67

 Administrativna

-0.66

 CreateTagHelper

-0.66

Efq

-0.65

хьтан

-0.63

HasBeenSet

-0.63

 informée

-0.63

POSITIVE LOGITS

wußt

0.28

 whom

0.27

 który

0.25

 mutat

0.25

 phổ

0.24

 StatefulWidget

0.23

 continuant

0.23

+#+#

0.23

who

0.23

bå

0.23

Activations Density 0.046%

function calls related to setting and adding properties or nodes in programming contexts

No Comments

No Known Activations