INDEX

Explanations

programming constructs related to return statements and variable assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

DropTable

-0.45

UnifiedTopology

-0.43

DataSetChanged

-0.43

-0.41

 study

-0.40

WinForms

-0.39

//

-0.36

 يتيمه

-0.36

study

-0.35

whence

-0.34

POSITIVE LOGITS

RefNanny

0.53

NgModule

0.53

localctx

0.50

featureID

0.48

 antaranya

0.47

SourceChecksum

0.45

ParallelGroup

0.45

Aholisi

0.44

 ujednoznacz

0.44

 apă

0.43

Activations Density 0.194%

programming constructs related to return statements and variable assignments

No Comments

No Known Activations