INDEX

Explanations

programming-related terms and constructs, particularly those related to classes and data structures

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

 initComponents

-0.66

 straws

-0.58

 Departmental

-0.58

 QtCore

-0.56

ignty

-0.55

TProtocol

-0.54

 universes

-0.54

 betweenstory

-0.53

 implore

-0.52

HomeAsUp

-0.52

POSITIVE LOGITS

 المعيارى

0.75

 يتيمه

0.58

tiba

0.57

філь

0.52

 Walkover

0.50

 خارجية

0.50

الإنجليزية

0.49

Література

0.49

 pair

0.49

 idéia

0.48

Activations Density 0.221%

programming-related terms and constructs, particularly those related to classes and data structures

No Comments

No Known Activations