INDEX

Explanations

programming and method call structures related to data handling and processing functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

IUrlHelper

-0.61

 jspb

-0.57

NameInMap

-0.52

WireFormatLite

-0.50

afficheront

-0.50

ستون

-0.50

ViewFeatures

-0.49

ModelForm

-0.48

AGG

-0.47

addLast

-0.47

POSITIVE LOGITS

 itſelf

0.78

RenderAtEndOf

0.78

ReusableCell

0.75

 myſelf

0.69

**********/

0.68

 pleaſure

0.65

 geschikt

0.65

()',

0.64

 raiſ

0.64

Efq

0.63

Activations Density 0.182%

programming and method call structures related to data handling and processing functions

No Comments

No Known Activations