INDEX

Explanations

numerical values indicating scores or leads in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 deleteUser

-0.67

клопе

-0.56

 للاسماء

-0.55

 getUser

-0.53

TabPage

-0.51

enek

-0.51

verständlich

-0.51

 userData

-0.50

Rhestr

-0.49

complexType

-0.48

POSITIVE LOGITS

TagMode

0.89

 JpaRepository

0.59

IBarButtonItem

0.57

 Komunikasi

0.56

scalatest

0.55

 predeceased

0.54

openzeppelin

0.54

 keting

0.53

ReusableCell

0.53

 followed

0.52

Activations Density 0.110%

numerical values indicating scores or leads in competitive contexts

No Comments

No Known Activations