INDEX

Explanations

references to data structures and function definitions in programming code

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

Pautan

-0.38

Investigators

-0.38

 wohin

-0.38

multicolumn

-0.36

stret

-0.36

 Gül

-0.35

 informée

-0.35

 Normdatei

-0.35

 stretch

-0.35

 يتيمه

-0.34

POSITIVE LOGITS

AccessorTable

0.56

ApiModelProperty

0.52

featureID

0.48

 resourceCulture

0.47

MemoryWarning

0.46

 iNdEx

0.46

MLLoader

0.44

JsonInclude

0.44

partements

0.43

 ricette

0.41

Activations Density 0.031%

references to data structures and function definitions in programming code

No Comments

No Known Activations