INDEX

Explanations

programming syntax and constructs related to function definitions and variable assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

RetentionPolicy

-0.60

TabStop

-0.57

utze

-0.56

TargetException

-0.54

bolista

-0.53

 CommandType

-0.52

insic

-0.52

 impacts

-0.51

thorpe

-0.51

GetProperty

-0.51

POSITIVE LOGITS

 Réponses

0.68

 AssemblyProduct

0.60

sproz

0.47

 >=",

0.47

Zodiac

0.46

 Autorizaciones

0.45

 خارجية

0.44

TypedDataSet

0.44

ęgn

0.44

nativeElement

0.44

Activations Density 0.324%

programming syntax and constructs related to function definitions and variable assignments

No Comments

No Known Activations