INDEX

Explanations

structures and syntax related to data representation and manipulation in programming

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

anzibar

-0.76

 chi̍t

-0.76

CONSIN

-0.67

 lakh

-0.66

 Panel

-0.65

део

-0.63

ikis

-0.62

FormTagHelper

-0.59

disha

-0.59

❉

-0.59

POSITIVE LOGITS

([

0.95

(["

0.69

 تعدى

0.67

 riguarda

0.65

ArgsConstructor

0.64

AutoresizingMask

0.63

StoryboardSegue

0.63

([

0.61

 Arrondissement

0.61

 אפ

0.60

Activations Density 0.083%

structures and syntax related to data representation and manipulation in programming

No Comments

No Known Activations